© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195904
    Prev
    Next
    INDEX
    Explanations

    Chinese and Japanese characters

    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_4_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
    the
    1.17
    та
    1.00
    یا
    0.97
    con
    0.96
    شون
    0.94
    可
    0.93
    νό
    0.92
    ਰ
    0.91
     arctic
    0.91
    ش
    0.89
    POSITIVE LOGITS
    2
    1.55
    uje
    1.23
    3
    1.16
    ↵
    1.14
    IM
    1.04
    1
    0.95
    5
    0.95
    ,
    0.94
    APP
    0.88
    IS
    0.87
    Activations Density 0.003%

    No Known Activations