© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46191
    Prev
    Next
    INDEX
    Explanations

    M&A, M&E, D&D, D&G

    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
    ៧
    0.50
     இதன்
    0.49
    ourt
    0.47
     фонбет
    0.46
    ())
    0.46
    ！)
    0.46
    ff
    0.46
    𝐨
    0.45
    em
    0.45
    य़ा
    0.44
    POSITIVE LOGITS
    ب
    0.60
     orchestras
    0.52
     conveyors
    0.50
    ν
    0.50
    િ
    0.50
    자
    0.49
     refreshments
    0.49
    Д
    0.48
     ambassadors
    0.47
     artworks
    0.47
    Activations Density 0.009%

    No Known Activations