© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213382
    Prev
    Next
    INDEX
    Explanations

    names entities

    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_50_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
    <0x86>
    0.46
     ಲಕ್ಷ
    0.44
     proverbial
    0.40
    eid
    0.40
    Moz
    0.40
    巴
    0.40
    hoed
    0.39
    Ricky
    0.39
    npj
    0.39
    వై
    0.39
    POSITIVE LOGITS
     attractions
    0.43
     critic
    0.42
     climber
    0.40
     V
    0.40
    덧
    0.39
    신기
    0.37
    ógrafo
    0.37
    сно
    0.37
     lamin
    0.37
    ജി
    0.36
    Activations Density 0.000%

    No Known Activations