© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192771
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    хие
    0.49
     игра
    0.48
     lanterns
    0.45
     plugs
    0.45
     подчи
    0.43
     lumin
    0.42
     pitches
    0.42
    뉴
    0.42
    重要な
    0.42
     firepower
    0.41
    POSITIVE LOGITS
    कारक
    0.52
    egen
    0.49
    existent
    0.49
    et
    0.48
    en
    0.48
     ⿱
    0.48
    LEMENT
    0.48
     _{\
    0.47
    สิน
    0.46
     empfehlen
    0.46
    Activations Density 0.000%

    No Known Activations