© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226785
    Prev
    Next
    INDEX
    Explanations

    distractions, statements, and non-English words

    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_10_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
    t
    0.13
    s
    0.12
    y
    0.11
     \[
    0.10
    tions
    0.10
     menghasilkan
    0.10
     to
    0.10
     When
    0.10
    yai
    0.10
    \]
    0.10
    POSITIVE LOGITS
    Casa
    0.14
    し
    0.14
    Мы
    0.13
    N
    0.12
    歌
    0.12
    G
    0.12
    Н
    0.12
    Не
    0.12
    Nella
    0.11
    Q
    0.11
    Activations Density 0.003%

    No Known Activations