© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46473
    Prev
    Next
    INDEX
    Explanations

    probabilistically

    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_22_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
    Spencer
    0.32
     Spencer
    0.31
     oscillations
    0.31
    ！」
    0.29
    !]
    0.29
    ダイ
    0.29
    Canada
    0.29
    !</
    0.28
    Mitchell
    0.28
    ক্ষণিক
    0.28
    POSITIVE LOGITS
    =?";
    0.34
     smatra
    0.32
     variously
    0.31
     Marcia
    0.30
     Bookstore
    0.30
     '?
    0.29
     तलब
    0.28
     ट्रेलर
    0.28
     العق
    0.28
    हे
    0.27
    Activations Density 0.000%

    No Known Activations