© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62039
    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_11_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
     destrucción
    0.57
    ان
    0.57
    ધુ
    0.56
    硬
    0.55
     مني
    0.55
    י
    0.53
    ر
    0.52
    슘
    0.52
     قيمة
    0.52
    詳
    0.52
    POSITIVE LOGITS
    ’
    0.73
    orks
    0.58
    ς
    0.58
    ’).
    0.56
    HttpContext
    0.56
     easements
    0.55
    ’)
    0.54
     collars
    0.54
    asting
    0.54
    DataAccess
    0.54
    Activations Density 0.000%

    No Known Activations