© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 214075
    Prev
    Next
    INDEX
    Explanations

    format

    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_43_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
    ိပ်
    0.42
    뿍
    0.40
     കേ
    0.38
     esempl
    0.38
    抔
    0.37
    CCO
    0.36
     שם
    0.35
     amn
    0.35
    🧥
    0.34
     സ്ഥ
    0.34
    POSITIVE LOGITS
     format
    2.55
    format
    2.22
     Format
    2.19
     formats
    2.05
    格式
    2.05
     формат
    2.05
     formato
    2.03
    Format
    1.99
     FORMAT
    1.97
     формате
    1.83
    Activations Density 0.008%

    No Known Activations