© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23508
    Prev
    Next
    INDEX
    Explanations

    Contact information

    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_56_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
    стая
    0.36
    tenant
    0.36
    কারি
    0.34
    лет
    0.34
     мире
    0.34
     дней
    0.33
     बीमारी
    0.32
    聞
    0.32
    \/}
    0.32
     чемпионате
    0.32
    POSITIVE LOGITS
    aszt
    0.37
     linebreak
    0.35
    Shoes
    0.34
    畚
    0.33
     শতকরা
    0.33
     Geraldine
    0.32
    MiddleCenter
    0.32
    ्थ
    0.32
     obič
    0.31
     इश्
    0.31
    Activations Density 0.258%

    No Known Activations