© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248086
    Prev
    Next
    INDEX
    Explanations

    finish

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     graduating
    0.37
    ലാണ്
    0.35
    itors
    0.32
    raint
    0.31
     लाय
    0.31
     बदमाशों
    0.31
     resigning
    0.31
    ляє
    0.30
    菅
    0.30
    郘
    0.30
    POSITIVE LOGITS
     fin
    3.73
     Fin
    3.36
    Fin
    3.20
    fin
    3.06
     FIN
    2.36
    FIN
    2.30
     fins
    1.92
    finn
    1.89
    フィン
    1.88
     фи
    1.86
    Activations Density 0.002%

    No Known Activations