© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193312
    Prev
    Next
    INDEX
    Explanations

    specifically mention

    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_9_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    am
    0.55
    ing
    0.54
    ेडकर
    0.54
    ショナル
    0.52
    HttpPut
    0.49
    ,
    0.49
    itories
    0.47
    🥯
    0.47
     अपराध
    0.47
    𒀊
    0.47
    POSITIVE LOGITS
     tenté
    0.47
     présentation
    0.45
     devez
    0.44
    פרי
    0.44
    応
    0.44
     dijo
    0.43
    0.43
     groupe
    0.43
     çiçek
    0.43
     znač
    0.42
    Activations Density 0.000%

    No Known Activations