© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81876
    Prev
    Next
    INDEX
    Explanations

    defining terms and conditions

    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_0_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
    á
    1.56
    AB
    1.49
     and
    1.48
    ﺍ
    1.44
    ip
    1.34
    PS
    1.31
     for
    1.28
    AV
    1.27
     &
    1.27
     மற்றும்
    1.25
    POSITIVE LOGITS
    ка
    1.82
    ي
    1.82
    но
    1.73
    ك
    1.60
    ش
    1.55
    ра
    1.55
    ۔
    1.49
    ።
    1.45
    ש
    1.41
    ativos
    1.39
    Activations Density 0.003%

    No Known Activations