© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109412
    Prev
    Next
    INDEX
    Explanations

    text with following punctuation

    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_1_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
     be
    1.31
    ur
    1.15
     to
    1.11
    al
    1.00
    in
    0.96
     have
    0.93
     de
    0.91
     a
    0.90
    us
    0.90
     from
    0.89
    POSITIVE LOGITS
    :
    1.49
    д
    1.26
    া
    1.06
    رمی
    1.05
     ﺍ
    1.02
     condizione
    1.00
     prawie
    0.98
     sorella
    0.98
    ﻪ
    0.98
     considerare
    0.96
    Activations Density 0.031%

    No Known Activations