© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33595
    Prev
    Next
    INDEX
    Explanations

    Law, fact, code

    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_3_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
     for
    0.79
     لأ
    0.77
     For
    0.58
     значення
    0.58
     ση
    0.56
    يته
    0.56
    诸
    0.56
     renom
    0.55
     ég
    0.55
     \;
    0.55
    POSITIVE LOGITS
    t
    0.75
    ل
    0.75
    ต
    0.74
    স
    0.70
    し
    0.70
    OL
    0.69
    UT
    0.68
    DC
    0.68
    تها
    0.68
    تان
    0.67
    Activations Density 0.012%

    No Known Activations