© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139495
    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_37_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
    开发的
    0.41
    ⭐️
    0.37
     বিষ
    0.36
    邈
    0.36
    出来的
    0.36
    ']))->
    0.35
    צת
    0.35
    毒
    0.35
    无论
    0.35
    enumeration
    0.35
    POSITIVE LOGITS
    جلس
    0.47
     Sessions
    0.40
     Asamblea
    0.40
    getSession
    0.38
     Sit
    0.37
    Sessions
    0.37
     sessions
    0.36
     barn
    0.36
     Leroy
    0.36
     अधिवेशन
    0.36
    Activations Density 0.000%

    No Known Activations