© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36566
    Prev
    Next
    INDEX
    Explanations

    Fried

    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_50_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
     Baird
    0.41
    الحضور
    0.40
     MFP
    0.39
     Dough
    0.39
     Fragmentation
    0.38
     Dunham
    0.38
    邹
    0.37
     الجرس
    0.37
     帽
    0.37
    getColumnIndex
    0.37
    POSITIVE LOGITS
     l
    0.50
     comm
    0.45
     ಲ
    0.41
     hourly
    0.40
    lich
    0.38
     jos
    0.38
     comet
    0.38
    ில
    0.38
     cedar
    0.38
    hourly
    0.37
    Activations Density 0.000%

    No Known Activations