© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85929
    Prev
    Next
    INDEX
    Explanations

    setlocal

    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_3_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
     in
    1.03
     (
    0.91
    在
    0.90
    ra
    0.79
     في
    0.77
    li
    0.74
    ne
    0.73
    lichen
    0.73
    (
    0.73
     در
    0.72
    POSITIVE LOGITS
    تری
    0.82
    。",
    0.77
    ิ
    0.73
    ע
    0.69
     rejuven
    0.67
     =",
    0.65
    ہ
    0.65
    ایر
    0.64
     تنظیم
    0.64
     pourcentage
    0.64
    Activations Density 0.005%

    No Known Activations