© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197757
    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_4_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
    または
    0.48
    М
    0.48
     \
    0.47
    Од
    0.46
    ל
    0.45
    டுகள்
    0.45
    ヤマ
    0.45
    コル
    0.44
     уйнау
    0.44
    性は
    0.44
    POSITIVE LOGITS
     ¨
    0.54
     Público
    0.51
     Chamberlain
    0.50
     kilka
    0.49
     Dali
    0.49
    sst
    0.48
     zich
    0.48
     kob
    0.48
    aya
    0.48
     fantástico
    0.46
    Activations Density 0.000%

    No Known Activations