© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130362
    Prev
    Next
    INDEX
    Explanations

    Ignores context or diversity

    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_1_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
    ,
    0.95
    اری
    0.94
    ੱਕ
    0.93
    ill
    0.92
    ials
    0.91
     bathrooms
    0.91
    illers
    0.88
     canons
    0.88
    向き
    0.87
    ای
    0.86
    POSITIVE LOGITS
    ي
    2.86
    i
    2.14
    י
    1.87
    2
    1.76
    ل
    1.66
    de
    1.63
    1
    1.63
    ع
    1.56
    ে
    1.52
    p
    1.50
    Activations Density 0.000%

    No Known Activations