© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22666
    Prev
    Next
    INDEX
    Explanations

    multi-language components

    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
    scoped
    0.41
    豆
    0.40
    ্টের
    0.40
    vay
    0.40
     Nes
    0.39
     beh
    0.39
     scoped
    0.38
    nesi
    0.38
    nestjs
    0.37
    heimer
    0.37
    POSITIVE LOGITS
    де
    0.47
    インタ
    0.41
    Of
    0.40
    데
    0.37
     Of
    0.36
    ДЕ
    0.36
    Analyzer
    0.36
    стя
    0.35
     oficio
    0.34
    о
    0.34
    Activations Density 0.003%

    No Known Activations