© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177617
    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_50_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
    シップ
    0.39
     Toda
    0.39
    skinned
    0.38
     Tand
    0.38
    ومت
    0.38
     Schritte
    0.38
    MS
    0.37
    ò
    0.37
    arity
    0.37
    спи
    0.36
    POSITIVE LOGITS
     газ
    0.47
    Sue
    0.42
    棣
    0.42
     Koe
    0.41
     căn
    0.39
    mae
    0.39
     pthread
    0.39
     mae
    0.39
     Sue
    0.39
    やや
    0.38
    Activations Density 0.000%

    No Known Activations