© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39879
    Prev
    Next
    INDEX
    Explanations

    reading books

    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_3_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
    as
    1.05
    is
    0.86
    ри
    0.77
     as
    0.71
    os
    0.70
    s
    0.70
    are
    0.69
    из
    0.68
    ियों
    0.68
    ur
    0.67
    POSITIVE LOGITS
    ﻴ
    0.77
     libert
    0.73
     restitu
    0.73
     locom
    0.69
     fech
    0.69
     liberación
    0.68
     finalizar
    0.68
     strada
    0.68
     motoc
    0.67
     scare
    0.66
    Activations Density 0.011%

    No Known Activations