© 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. 122097
    Prev
    Next
    INDEX
    Explanations

    crimson tide

    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
    t
    0.87
    ৯
    0.82
    ৩
    0.81
    ৪
    0.79
    ৭
    0.76
    ۹
    0.73
    ১৫
    0.70
    Т
    0.69
    ン
    0.68
    Ста
    0.67
    POSITIVE LOGITS
     (
    0.76
    ,
    0.58
     won
    0.56
    มั่น
    0.54
    iong
    0.53
     <
    0.53
     [
    0.53
     durée
    0.53
     fragmentation
    0.53
     vague
    0.52
    Activations Density 0.000%

    No Known Activations