© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132000
    Prev
    Next
    INDEX
    Explanations

    give it a shot

    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_6_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
     are
    0.87
    im
    0.81
    ic
    0.79
    ీ
    0.76
    มี
    0.75
     be
    0.75
     sàng
    0.73
    \
    0.73
     have
    0.71
     vý
    0.71
    POSITIVE LOGITS
    re
    0.99
    ;
    0.98
    Y
    0.97
    id
    0.92
    ра
    0.92
    ,
    0.91
    DA
    0.90
    Plus
    0.89
    foreground
    0.89
    の
    0.88
    Activations Density 0.000%

    No Known Activations