© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111305
    Prev
    Next
    INDEX
    Explanations

    GC, BGC, UGC, RGCs

    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_2_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
     a
    1.20
    .
    1.16
    ви
    0.96
     racquet
    0.93
    १९
    0.91
     νέα
    0.91
     ating
    0.91
    밂
    0.91
    .}
    0.90
     on
    0.89
    POSITIVE LOGITS
    t
    1.66
    ون
    1.34
    ো
    1.28
     in
    1.26
    ุ
    1.23
    arı
    1.14
    tų
    1.14
    2
    1.13
    在
    1.12
    もら
    1.09
    Activations Density 0.000%

    No Known Activations