© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41073
    Prev
    Next
    INDEX
    Explanations

    not too

    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_11_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
    s
    0.70
    ড়যন্ত্র
    0.54
     beve
    0.52
     incentiv
    0.51
    \
    0.51
    rs
    0.51
    프
    0.51
    ൺ
    0.51
    ink
    0.50
     confianza
    0.50
    POSITIVE LOGITS
    त
    0.60
    uais
    0.56
    ку
    0.54
     Те
    0.51
     созда
    0.51
    ﻰ
    0.51
     мем
    0.50
     Taxonomic
    0.50
    τερα
    0.50
     काही
    0.49
    Activations Density 0.002%

    No Known Activations