© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253997
    Prev
    Next
    INDEX
    Explanations

    book and business

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Duckworth
    0.30
     Thes
    0.30
     Role
    0.29
     
    0.27
    AntiForgery
    0.27
    ゝ
    0.27
    𝐆
    0.27
     rh
    0.27
     mc
    0.27
     shellcheck
    0.27
    POSITIVE LOGITS
     basking
    0.31
    श्त
    0.28
    .',
    0.27
    .]:
    0.27
    ."],
    0.26
     hver
    0.26
    .}
    0.26
    ಝ
    0.26
    “,
    0.26
    間に
    0.25
    Activations Density 0.001%

    No Known Activations