© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198922
    Prev
    Next
    INDEX
    Explanations

    North Point Lighthouse

    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_4_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
    p
    1.01
    م
    1.00
    m
    0.98
     of
    0.97
     on
    0.96
    З
    0.93
    ي
    0.92
     in
    0.84
    м
    0.82
    ("
    0.82
    POSITIVE LOGITS
    0.89
    ing
    0.83
    ann
    0.71
    igence
    0.69
    '
    0.69
     система
    0.68
     знать
    0.67
    σιν
    0.66
    n
    0.66
    ácter
    0.65
    Activations Density 0.001%

    No Known Activations