© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12816
    Prev
    Next
    INDEX
    Explanations

    technical terms and code

    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_40_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
    एमसी
    0.30
     Tenn
    0.29
     ////
    0.29
     آپریشن
    0.29
     mał
    0.29
    毉
    0.29
     colección
    0.28
     operaciones
    0.28
     เปลี่ยน
    0.28
     תש
    0.28
    POSITIVE LOGITS
    రిగి
    0.37
     skid
    0.34
    สอบ
    0.32
    ⁹
    0.32
     свер
    0.32
    parse
    0.31
     Reeves
    0.31
     Skid
    0.31
     диви
    0.29
    divisor
    0.29
    Activations Density 0.003%

    No Known Activations