© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171533
    Prev
    Next
    INDEX
    Explanations

    layout management

    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_20_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
     цвет
    0.38
     ಉತ್ಪನ್ನ
    0.38
     elementi
    0.38
     Highest
    0.37
     CULTURE
    0.37
     bitch
    0.36
     специфи
    0.36
    戻
    0.36
    NAM
    0.35
     muita
    0.35
    POSITIVE LOGITS
    registerTask
    0.40
     iterates
    0.40
    ล
    0.39
     animated
    0.39
    Pumpkin
    0.39
    ਹੀਂ
    0.38
    เ
    0.37
    /"+
    0.37
     Pumpkin
    0.37
    锰
    0.37
    Activations Density 0.002%

    No Known Activations