© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200332
    Prev
    Next
    INDEX
    Explanations

    Migration and autoload

    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_37_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
     scrambling
    0.37
     поговори
    0.36
    φ
    0.36
     wrestle
    0.36
     প্রশ্নে
    0.36
     scramble
    0.35
     posisi
    0.35
    义务
    0.35
    asmine
    0.34
    ☟
    0.34
    POSITIVE LOGITS
     ഉട
    0.37
     кру
    0.37
     invasion
    0.37
     hui
    0.37
     BOD
    0.37
    мей
    0.36
     zł
    0.36
     Moderne
    0.36
     දී
    0.36
    द्दीन
    0.36
    Activations Density 0.000%

    No Known Activations