© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87929
    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_23_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
    uyết
    0.46
    Che
    0.43
     poslední
    0.42
     че
    0.41
    ^{\
    0.40
    Production
    0.40
     medzi
    0.40
     бла
    0.40
    DataGridView
    0.39
    льні
    0.39
    POSITIVE LOGITS
     travaillons
    0.50
     Spelling
    0.46
    carrito
    0.46
     धमकी
    0.45
     MIME
    0.44
     concealment
    0.44
     Impressions
    0.44
    ાળા
    0.43
     ყ
    0.43
     Stripes
    0.42
    Activations Density 0.000%

    No Known Activations