© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212166
    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_19_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
     encuent
    0.46
    ၤ
    0.45
    必須
    0.44
    ဆေး
    0.44
    適合
    0.43
     می‌ده
    0.42
    你可以
    0.42
    找到了
    0.42
    頑
    0.41
    具体的
    0.41
    POSITIVE LOGITS
    нской
    0.47
    iton
    0.45
    untlet
    0.44
     docente
    0.44
     stopp
    0.43
    ोत
    0.43
    inary
    0.43
    acay
    0.42
     Аль
    0.41
    CLAS
    0.41
    Activations Density 0.000%

    No Known Activations