© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35937
    Prev
    Next
    INDEX
    Explanations

    mean field theory or meaning of life

    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
    g
    0.79
    på
    0.78
    𝗣
    0.75
    grained
    0.74
    𝗴
    0.73
    𝗚
    0.73
    painted
    0.73
    effort
    0.72
    gne
    0.71
    grave
    0.71
    POSITIVE LOGITS
    0.95
    ุ
    0.84
    י
    0.77
    υ
    0.74
    н
    0.73
    น
    0.72
    ื่อน
    0.67
     F
    0.64
     หมาย
    0.64
     Ba
    0.63
    Activations Density 0.007%

    No Known Activations