© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161424
    Prev
    Next
    INDEX
    Explanations

    Day 2

    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_31_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
    ->
    0.37
     dipl
    0.37
     joined
    0.36
     select
    0.36
     segmented
    0.36
     first
    0.36
     Recognition
    0.36
     Hidden
    0.36
    ースト
    0.36
     আশ্রয়
    0.36
    POSITIVE LOGITS
    早上
    0.42
    每天
    0.38
    早餐
    0.38
    morning
    0.37
    }((
    0.37
     ಕಬ್ಬಿಣ
    0.37
    منت
    0.36
    LIS
    0.36
    issage
    0.36
    第二天
    0.36
    Activations Density 0.002%

    No Known Activations