© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137950
    Prev
    Next
    INDEX
    Explanations

    performers and music hall

    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_12_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
     \,.
    0.54
     werewolf
    0.53
     €,
    0.52
    शुदा
    0.52
    িনী
    0.52
     renderEncoder
    0.52
     जैसे
    0.52
     כמו
    0.51
    เช่น
    0.50
     waterfowl
    0.50
    POSITIVE LOGITS
    Z
    0.67
    K
    0.61
    GR
    0.59
    force
    0.59
    RUN
    0.56
    )
    0.55
    makes
    0.54
    kommt
    0.51
    N
    0.50
    H
    0.50
    Activations Density 0.000%

    No Known Activations