© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78144
    Prev
    Next
    INDEX
    Explanations

    if __name__ == "main"

    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_0_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
    2.11
    od
    2.00
    ون
    1.77
    কে
    1.72
    ן
    1.66
    on
    1.64
    나
    1.62
    et
    1.56
    c
    1.54
    ت
    1.48
    POSITIVE LOGITS
    し
    1.60
    ↵
    1.48
     concili
    1.45
    G
    1.41
    。
    1.38
    O
    1.37
    E
    1.31
    ।
    1.31
    しさ
    1.30
     (
    1.28
    Activations Density 0.001%

    No Known Activations