© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42285
    Prev
    Next
    INDEX
    Explanations

    a given phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    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
     "}
    0.75
    []}
    0.70
     you
    0.67
    ｱ
    0.67
     poté
    0.66
    ^{*}}
    0.64
    
    0.62
     *}
    0.62
     вашего
    0.61
     الاشتراك
    0.61
    POSITIVE LOGITS
    د
    1.13
    ב
    1.13
    ب
    1.05
    то
    0.99
    д
    0.99
    та
    0.96
    ת
    0.92
    ع
    0.91
    ?
    0.89
    ش
    0.89
    Activations Density 0.006%

    No Known Activations