© 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. 57295
    Prev
    Next
    INDEX
    Explanations

    connection and linkage

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ;
    0.68
    سی
    0.64
    こんにちは
    0.58
    נות
    0.57
    私は
    0.56
    !;
    0.56
    צי
    0.55
     BLUE
    0.55
    glich
    0.55
    لیس
    0.55
    POSITIVE LOGITS
     gedacht
    0.52
    ির্ব
    0.52
     ប
    0.52
     удовле
    0.52
     diminue
    0.50
     Ř
    0.49
    lara
    0.49
    sdk
    0.49
     Осо
    0.49
    ěla
    0.49
    Activations Density 0.000%

    No Known Activations