© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15287
    Prev
    Next
    INDEX
    Explanations

    self-repair, themselves, itself

    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_13_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
     Orbit
    0.53
     Sell
    0.53
     Smell
    0.52
    }",
    0.51
    ıştı
    0.51
    ."),
    0.50
     Аль
    0.50
     Orchard
    0.50
     Ex
    0.50
     Forms
    0.50
    POSITIVE LOGITS
     utilitarian
    0.56
    ောင့်
    0.54
     inequality
    0.50
    WEST
    0.48
    梯度
    0.48
     socioeconomic
    0.48
    墨
    0.48
    ם
    0.47
     diting
    0.46
    ן
    0.46
    Activations Density 0.000%

    No Known Activations