© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 59595
    Prev
    Next
    INDEX
    Explanations

    catsuit, catsuits, jumpsuit, jumpsuits

    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_11_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
     पीने
    0.48
    sembles
    0.47
    Exper
    0.47
    iones
    0.47
    exper
    0.46
    ifest
    0.45
    Node
    0.45
    (
    0.45
    ede
    0.44
    (`/
    0.44
    POSITIVE LOGITS
    ง
    0.62
     Игра
    0.55
     on
    0.54
     فونبټ
    0.54
    ну
    0.53
     রে
    0.53
    💴
    0.53
     प्रमेय
    0.52
     rt
    0.52
    لمانيا
    0.52
    Activations Density 0.000%

    No Known Activations