© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4159
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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_40_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
    跇
    0.33
    𒌷
    0.32
    صف
    0.32
     மூ
    0.29
     امریکی
    0.29
    डील
    0.29
    ն
    0.29
    Screen
    0.28
     ஈ
    0.28
     promises
    0.27
    POSITIVE LOGITS
    하도록
    0.37
    Ding
    0.32
    fors
    0.31
     Lyman
    0.30
     CAPS
    0.30
    container
    0.30
     Aux
    0.30
    ANGE
    0.29
    visitor
    0.29
     भोज
    0.29
    Activations Density 0.007%

    No Known Activations