© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154426
    Prev
    Next
    INDEX
    Explanations

    a

    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_60_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
    个人
    0.52
    裡
    0.49
    ime
    0.49
    一
    0.48
    边
    0.47
     edge
    0.47
     an
    0.47
    一条
    0.46
    一道
    0.45
    ik
    0.45
    POSITIVE LOGITS
    נות
    0.45
    נים
    0.43
    вина
    0.43
    נ
    0.43
    <0x98>
    0.40
    Ž
    0.39
     ورلڈ
    0.39
    মানব
    0.39
    вани
    0.38
    newswire
    0.38
    Activations Density 0.001%

    No Known Activations