© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46269
    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_13_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
    ა
    0.55
    স
    0.54
    כש
    0.54
    ুঁ
    0.49
    в
    0.48
     Former
    0.48
     Truy
    0.47
    룺
    0.47
    יש
    0.46
     Consider
    0.46
    POSITIVE LOGITS
     start
    0.48
     translocation
    0.48
    RI
    0.47
     груп
    0.46
    ،
    0.46
     lock
    0.46
     ذ
    0.46
     الص
    0.46
     شرا
    0.46
     slid
    0.46
    Activations Density 0.000%

    No Known Activations