© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4246
    Prev
    Next
    INDEX
    Explanations

    .com, .ai, .net, .cn

    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_40_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
     type
    0.62
     fn
    0.62
    type
    0.54
    fn
    0.52
    Type
    0.48
     Type
    0.47
     Fn
    0.46
     FN
    0.45
     bn
    0.44
    #[
    0.44
    POSITIVE LOGITS
    別途
    0.38
    dde
    0.38
    zaXR
    0.37
    лям
    0.36
    ব্যাপ
    0.36
    くれて
    0.36
    뭔
    0.35
    ึง
    0.35
     lái
    0.35
    原則
    0.34
    Activations Density 0.048%

    No Known Activations