© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43822
    Prev
    Next
    INDEX
    Explanations

    Meta AI

    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_3_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
    る
    0.61
    il
    0.60
    явить
    0.55
    ги
    0.54
    尸
    0.54
    sg
    0.52
    ින
    0.52
    ْم
    0.52
    ųjų
    0.52
    et
    0.51
    POSITIVE LOGITS
    ب
    0.66
    f
    0.66
    ী
    0.65
    ıları
    0.63
     a
    0.62
     تأثير
    0.62
     scuole
    0.62
     adecuada
    0.61
    公司
    0.61
     σε
    0.61
    Activations Density 0.003%

    No Known Activations