© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177871
    Prev
    Next
    INDEX
    Explanations

    stock ratings and recommendations

    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_29_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
    ɲ
    0.40
    사용
    0.40
     ዋና
    0.39
     باستخدام
    0.39
    当店
    0.38
    નું
    0.37
    ($_
    0.37
     using
    0.37
    の使用
    0.36
    实在
    0.36
    POSITIVE LOGITS
     antes
    0.38
     colocadas
    0.36
     सोचा
    0.35
    滁
    0.35
     vértice
    0.34
     Hamburger
    0.34
     vox
    0.34
     aumentada
    0.34
     Ba
    0.33
     Fo
    0.33
    Activations Density 0.001%

    No Known Activations