© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8523
    Prev
    Next
    INDEX
    Explanations

    circularity, circuits, loops

    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_40_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
    雵
    0.38
     Mou
    0.35
    رفت
    0.35
     المؤس
    0.35
     ബ്ല
    0.35
    elhos
    0.34
    血压
    0.34
     استف
    0.33
     हिम
    0.33
     सर्जरी
    0.33
    POSITIVE LOGITS
     split
    0.39
     circuits
    0.39
     circle
    0.36
     CIRCUIT
    0.36
    圈
    0.36
     loop
    0.35
     climbing
    0.35
     circles
    0.35
     circuit
    0.34
     flute
    0.34
    Activations Density 0.499%

    No Known Activations