© 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. 12080
    Prev
    Next
    INDEX
    Explanations

    gluten-free

    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
    ཝ
    0.54
    یت
    0.52
     هیچ
    0.52
    Ბ
    0.49
     जहां
    0.48
    Advantages
    0.48
    注意事项
    0.46
    アイテム
    0.46
    ("+
    0.46
    인
    0.46
    POSITIVE LOGITS
     baker
    0.60
    isjon
    0.58
     ті
    0.55
     мі
    0.54
     δι
    0.54
     simplex
    0.54
    is
    0.52
     tortillas
    0.52
     горо
    0.52
     starch
    0.52
    Activations Density 0.001%

    No Known Activations