© 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. 223011
    Prev
    Next
    INDEX
    Explanations

    out police, are courtesy, are open, out of, are there, are preparing, are committed, are drawn

    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
    的
    0.99
    （
    0.97
    ス
    0.96
    ・
    0.87
    在
    0.86
    с
    0.84
    ни
    0.84
    會
    0.84
    -
    0.82
    의
    0.82
    POSITIVE LOGITS
    idän
    0.82
     છીએ
    0.71
     канторы
    0.71
     elastomer
    0.68
     bolog
    0.66
     způ
    0.64
     woolen
    0.63
     infek
    0.62
    icleta
    0.62
    eket
    0.61
    Activations Density 0.004%

    No Known Activations