© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143745
    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_0_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
    ⅲ
    0.53
    ف
    0.52
     ንጥረ
    0.50
     biochemistry
    0.48
     Biochemistry
    0.48
     gamanam
    0.47
     पीएचडी
    0.45
     miejscu
    0.43
     Phas
    0.43
    啟用
    0.43
    POSITIVE LOGITS
    algar
    0.52
    요일
    0.51
    다
    0.49
     zu
    0.48
     công
    0.48
    лён
    0.48
    ING
    0.48
     maksud
    0.47
    ри
    0.47
     gia
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.