© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49975
    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_10_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
    ↵
    0.59
    o
    0.57
    k
    0.54
    ↵↵
    0.48
    i
    0.47
    要
    0.46
     I
    0.44
    ,
    0.44
     wars
    0.43
       
    0.43
    POSITIVE LOGITS
     कॉंग्रेस
    0.56
    gomery
    0.55
    ผู้ชม
    0.54
    iguo
    0.51
     ምግብ
    0.50
     जापान
    0.49
    getImageFolder
    0.49
    िटीज
    0.48
     पोप
    0.48
     catfish
    0.48
    Activations Density 0.000%

    No Known Activations