© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26692
    Prev
    Next
    INDEX
    Explanations

    Bi

    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
    Negative Logits
     empirically
    0.39
    ব্ধ
    0.38
     sometime
    0.37
    عبة
    0.37
    ￥
    0.37
     representado
    0.36
    WillAppear
    0.36
     FRAN
    0.35
    حدى
    0.35
    mystery
    0.35
    POSITIVE LOGITS
     elementos
    0.40
     Garrison
    0.37
     Violent
    0.36
    戎
    0.36
     violent
    0.36
     printing
    0.36
     Layer
    0.35
     Wik
    0.35
     Xun
    0.35
    িস্থ
    0.35
    Activations Density 0.011%

    No Known Activations