© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88620
    Prev
    Next
    INDEX
    Explanations

    human

    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_11_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
    ategori
    0.65
    лна
    0.57
    ಣ
    0.57
    䒠
    0.57
    িক
    0.56
    狧
    0.55
    ্ল্ড
    0.54
    elliptic
    0.54
     സ്ത്രീ
    0.53
    enumValues
    0.53
    POSITIVE LOGITS
    He
    0.66
     control
    0.61
    on
    0.57
    We
    0.56
    By
    0.56
    &
    0.55
     de
    0.55
    Buck
    0.55
     c
    0.54
    是为了
    0.54
    Activations Density 0.018%

    No Known Activations