© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193530
    Prev
    Next
    INDEX
    Explanations

    -Wall for all warnings

    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_9_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
    ँ
    0.58
    ロップ
    0.57
    に
    0.56
    र्या
    0.55
    ходов
    0.55
     sociais
    0.53
     προσωπ
    0.53
    ми
    0.53
     型
    0.52
     inic
    0.52
    POSITIVE LOGITS
    al
    0.88
    en
    0.85
    t
    0.80
    ac
    0.77
    at
    0.76
    s
    0.75
    ol
    0.74
    d
    0.70
    st
    0.70
    l
    0.69
    Activations Density 0.000%

    No Known Activations