© 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. 51386
    Prev
    Next
    INDEX
    Explanations

    all, 拖, 繫, 所

    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
    取り
    0.56
    出
    0.54
    従
    0.54
    են
    0.52
     hóa
    0.52
    示す
    0.51
     desolate
    0.51
    يريا
    0.51
    ίν
    0.51
    ından
    0.50
    POSITIVE LOGITS
    Don
    0.62
    {
    0.61
    an
    0.61
    Color
    0.61
    KA
    0.61
    MA
    0.57
    Name
    0.56
    VS
    0.55
    Anderson
    0.54
    Firefox
    0.54
    Activations Density 0.001%

    No Known Activations