© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193473
    Prev
    Next
    INDEX
    Explanations

    code syntax detection

    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_9_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ের
    0.79
    theon
    0.77
    を有
    0.75
    ς
    0.72
    வற்ற
    0.71
    ים
    0.71
     پیسو
    0.69
     stanu
    0.66
     forgo
    0.66
    を表
    0.66
    POSITIVE LOGITS
    lc
    1.22
    ك
    1.11
    ل
    1.02
    د
    1.01
    خ
    1.00
    anc
    0.98
    ق
    0.98
    ।
    0.98
    ट
    0.96
    0
    0.94
    Activations Density 0.012%

    No Known Activations