© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137117
    Prev
    Next
    INDEX
    Explanations

    transformer blocks and layers

    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_12_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
    c
    0.54
    inaire
    0.54
    人都
    0.53
     योग
    0.52
     свиде
    0.52
     составля
    0.47
     destaca
    0.47
    éré
    0.46
     кай
    0.46
     исследования
    0.46
    POSITIVE LOGITS
    棗
    0.57
     lumps
    0.57
     corrugated
    0.55
    🆁
    0.54
    BOOT
    0.54
     Direktor
    0.54
     candies
    0.54
    DrvGPIO
    0.54
     daffodils
    0.53
     bituminous
    0.53
    Activations Density 0.013%

    No Known Activations