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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27342
    Prev
    Next
    INDEX
    Explanations

    book, textbook, manuals

    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_10_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
    s
    0.65
    ە
    0.59
    p
    0.58
     table
    0.57
    ment
    0.56
    se
    0.55
    t
    0.55
    ség
    0.54
    ij
    0.53
    ek
    0.52
    POSITIVE LOGITS
     अखबार
    0.59
    帙
    0.58
    이나
    0.56
     bookshelves
    0.54
    зре
    0.53
    Пре
    0.53
    Од
    0.53
    얇
    0.52
    Verlag
    0.51
    이
    0.51
    Activations Density 0.044%

    No Known Activations