© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149954
    Prev
    Next
    INDEX
    Explanations

    来

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    说
    1.31
    說
    1.29
    说是
    0.93
    說是
    0.93
    自
    0.90
     say
    0.88
     saying
    0.88
    看
    0.86
    說明
    0.86
     Say
    0.76
    POSITIVE LOGITS
    Electric
    0.49
    electric
    0.43
     മണിക്ക
    0.41
     Electric
    0.40
     ELECTRIC
    0.40
    Carlo
    0.40
    ✯
    0.40
    dou
    0.39
    sign
    0.38
    得
    0.38
    Activations Density 0.000%

    No Known Activations