© 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. 46571
    Prev
    Next
    INDEX
    Explanations

    t variable in formulas

    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
    ва
    0.93
    е
    0.89
    ى
    0.86
    ат
    0.86
    ка
    0.83
    те
    0.82
    ни
    0.82
    ம்
    0.79
    ти
    0.79
    ους
    0.77
    POSITIVE LOGITS
    i
    1.48
    z
    1.13
    to
    1.10
    n
    1.09
    ي
    1.01
     {
    0.93
    un
    0.91
    ن
    0.89
    ll
    0.88
    can
    0.88
    Activations Density 0.017%

    No Known Activations