© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 343
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    el
    1.68
    er
    1.64
    t
    1.62
    in
    1.59
    en
    1.57
    on
    1.50
    ان
    1.50
    ec
    1.47
    y
    1.41
    o
    1.41
    POSITIVE LOGITS
    ം
    1.89
    ை
    1.65
    ュー
    1.59
    zelf
    1.58
    すすめ
    1.46
    とその
    1.46
    า
    1.43
    呦
    1.41
    ों
    1.40
    ться
    1.38
    Activations Density 1.915%

    No Known Activations