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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 11630
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )');
    0.74
    帙
    0.72
    მი
    0.71
    ১
    0.71
    }}[
    0.70
     праців
    0.70
    粋
    0.69
    商品の
    0.69
    披露
    0.68
    ্ঞ
    0.67
    POSITIVE LOGITS
     नरम
    0.72
    o
    0.71
    en
    0.69
    helle
    0.69
    u
    0.68
    M
    0.68
    oo
    0.68
    y
    0.68
    et
    0.67
     HomeComponent
    0.67
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.