© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26404
    Prev
    Next
    INDEX
    Explanations

    Curriculum Vitae

    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
    un
    0.86
    m
    0.81
    на
    0.77
    id
    0.76
     전에
    0.75
    ی
    0.74
    It
    0.73
    re
    0.72
    previously
    0.68
    s
    0.66
    POSITIVE LOGITS
     by
    0.91
     School
    0.77
     Groundwater
    0.72
     as
    0.68
     Lender
    0.67
     Bank
    0.66
    لة
    0.64
     UNICEF
    0.64
     Leibniz
    0.63
     n
    0.62
    Activations Density 0.000%

    No Known Activations