© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88595
    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
     اله
    0.50
    门
    0.46
     архів
    0.43
    썻
    0.43
     获取
    0.42
     Université
    0.42
    拓展
    0.42
    翀
    0.42
     berjudul
    0.42
    徃
    0.41
    POSITIVE LOGITS
     veneer
    0.47
     veneers
    0.46
     Brum
    0.45
    ar
    0.44
    kona
    0.44
     matar
    0.44
     humidity
    0.44
    mati
    0.44
    ri
    0.44
    Н
    0.43
    Activations Density 0.000%

    No Known Activations