© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24031
    Prev
    Next
    INDEX
    Explanations

    pi

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    าร
    0.38
     Forks
    0.36
    柊
    0.35
     vene
    0.34
    Pic
    0.33
     сил
    0.33
    Wedgwood
    0.33
    Guess
    0.33
     हीरा
    0.33
    ເວ
    0.33
    POSITIVE LOGITS
     pě
    1.34
     п
    1.29
     π
    1.21
     pię
    1.06
     ఐ
    1.00
     пят
    0.98
     пя
    0.94
     pią
    0.93
     pie
    0.91
     ಐ
    0.90
    Activations Density 0.096%

    No Known Activations