© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154236
    Prev
    Next
    INDEX
    Explanations

    document file type

    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_50_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
     青
    0.39
     domani
    0.39
    医
    0.39
    培
    0.37
     pecans
    0.37
    hamed
    0.36
     Wilkes
    0.36
     relevantes
    0.36
     mannit
    0.36
    ຕ
    0.36
    POSITIVE LOGITS
    Waterfall
    0.42
    Ky
    0.42
     Waterfall
    0.40
    CED
    0.40
    Methoxy
    0.40
     CED
    0.39
    KY
    0.38
    Cedar
    0.38
    adjustable
    0.38
    σει
    0.38
    Activations Density 0.003%

    No Known Activations