© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113158
    Prev
    Next
    INDEX
    Explanations

    graphics driver or cards

    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_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    i
    2.17
    ي
    1.73
    י
    1.52
    ে
    1.48
    n
    1.43
    y
    1.36
    ו
    1.30
    ი
    1.16
    ва
    1.16
    ii
    1.16
    POSITIVE LOGITS
     to
    1.47
    UT
    1.16
    س
    1.09
     the
    1.08
     as
    1.04
    ায়
    0.98
     congreg
    0.94
    AD
    0.94
    OO
    0.93
    ется
    0.93
    Activations Density 0.007%

    No Known Activations