🔎 EmbeddingGemma Semantic Search

Runs entirely in your browser with Transformers.js and EmbeddingGemma-300M (ONNX). No server calls — the model downloads and runs on your device.

The model's ONNX graph already L2-normalizes its output embedding internally (mean-pool → 2 dense layers → divide by L2 norm), so with the toggle on and metric = cosine, this reduces to a plain dot product on unit vectors. Turn the toggle off or switch metric to see the effect of normalization and metric choice directly.

Model not loaded