© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12085
    Prev
    Next
    INDEX
    Explanations

    Gemma team at Google DeepMind

    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_13_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
     வளாக
    0.31
    在于
    0.31
     aperiam
    0.31
     स
    0.30
    neath
    0.29
     underneath
    0.29
    พื้นที่
    0.29
    spreading
    0.29
     Behind
    0.29
     Alongside
    0.29
    POSITIVE LOGITS
    не
    0.33
    =
    0.33
    меры
    0.33
    k
    0.33
    OS
    0.33
    ту
    0.33
    因子
    0.33
    па
    0.32
    ҷи
    0.32
    ।-
    0.32
    Activations Density 0.019%

    No Known Activations