© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86730
    Prev
    Next
    INDEX
    Explanations

    book titles or specific books

    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_3_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
    bindingFields
    0.68
    ⠑
    0.61
    蘚
    0.61
     запо
    0.59
     hơn
    0.57
     صلى
    0.57
    кове
    0.56
     август
    0.55
    don
    0.55
     разви
    0.55
    POSITIVE LOGITS
    _
    0.78
    DC
    0.77
    \
    0.73
    re
    0.68
    ors
    0.68
    ID
    0.66
    ي
    0.65
     as
    0.63
    هم
    0.63
    م
    0.63
    Activations Density 0.001%

    No Known Activations