© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11129
    Prev
    Next
    INDEX
    Explanations

    LMSYS website and chat.lmsys.org

    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_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
     있어
    0.56
    ieniu
    0.55
    awatan
    0.50
     Kurulu
    0.50
    ę
    0.50
    preuve
    0.49
    niveau
    0.49
     Prozesse
    0.48
    pekte
    0.47
     প্রতিক্রিয়া
    0.47
    POSITIVE LOGITS
     arrests
    0.42
    ang
    0.41
     lời
    0.41
     Exodus
    0.41
     crash
    0.40
    獭
    0.40
    ir
    0.40
     coma
    0.39
    <0x81>
    0.39
     cram
    0.39
    Activations Density 0.016%

    No Known Activations