© 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. 24330
    Prev
    Next
    INDEX
    Explanations

    oh my gosh

    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
    \
    0.75
    ne
    0.73
    üm
    0.71
    Dü
    0.66
    ।
    0.65
    se
    0.64
    "
    0.63
    á
    0.63
    A
    0.63
    ete
    0.61
    POSITIVE LOGITS
    具体的な
    0.59
     Thumbnail
    0.57
     কাজী
    0.55
    at
    0.54
    точно
    0.52
    িয়ার
    0.52
    یط
    0.52
     fanciful
    0.52
    ższ
    0.51
    と呼ばれる
    0.51
    Activations Density 0.015%

    No Known Activations