© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52744
    Prev
    Next
    INDEX
    Explanations

    questions about that

    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_31_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
     swat
    0.32
    اعة
    0.30
     நிய
    0.30
    தர
    0.29
    椇
    0.29
     punctuated
    0.28
     безу
    0.28
     ввод
    0.27
    鸵
    0.27
     snatched
    0.27
    POSITIVE LOGITS
     ix
    0.30
     Villeneuve
    0.29
    န်
    0.29
    ativos
    0.29
    种子
    0.29
    촌
    0.29
    يكي
    0.29
     adherent
    0.29
     arro
    0.28
    relatively
    0.28
    Activations Density 0.002%

    No Known Activations