© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211520
    Prev
    Next
    INDEX
    Explanations

    comparison or contrast markers

    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_20_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
    unique
    0.45
    Node
    0.43
    ◡
    0.42
    requently
    0.39
    пора
    0.39
    сию
    0.39
     combinado
    0.39
    subfigure
    0.39
     transacción
    0.38
    engineered
    0.38
    POSITIVE LOGITS
     цьому
    0.40
     Fizz
    0.40
    หมู่
    0.39
     Barnes
    0.39
    浑
    0.38
    Під
    0.38
     officielles
    0.38
     বছরের
    0.38
     Μα
    0.38
     titulada
    0.38
    Activations Density 0.021%

    No Known Activations