© 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. 32649
    Prev
    Next
    INDEX
    Explanations

    html label and input tags

    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
     check
    0.35
    சு
    0.34
    Scal
    0.32
    Check
    0.31
     Check
    0.31
    Рас
    0.31
     الشع
    0.31
    ("/
    0.30
     Рас
    0.30
    checkable
    0.30
    POSITIVE LOGITS
    뛴
    0.37
     منهج
    0.35
    キュリティ
    0.34
     корне
    0.33
    igde
    0.33
     নিত
    0.32
     뛰
    0.30
     ferns
    0.30
    튠
    0.30
     KK
    0.30
    Activations Density 0.002%

    No Known Activations