© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194854
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_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
    ン
    0.54
    ن
    0.48
     ocurr
    0.48
    破
    0.47
    نم
    0.47
    ี
    0.46
    ى
    0.45
    ホン
    0.45
     ocur
    0.45
    يد
    0.44
    POSITIVE LOGITS
    ađ
    0.52
    amide
    0.48
    ErrorClazz
    0.48
    എന്ന
    0.47
     그거
    0.47
     galer
    0.47
     আসেন
    0.46
    存档备份
    0.46
    ancellation
    0.46
    amblea
    0.46
    Activations Density 0.000%

    No Known Activations