© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143036
    Prev
    Next
    INDEX
    Explanations

    fats

    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_0_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
    ки
    1.66
    n
    1.66
    ר
    1.63
    iy
    1.57
    र
    1.50
    ről
    1.37
    r
    1.34
    ﺍ
    1.34
    g
    1.33
    iot
    1.31
    POSITIVE LOGITS
    人
    1.32
    в
    1.29
    ación
    1.24
     Daarnaast
    1.08
    ма
    1.05
    мі
    1.03
    であった
    1.02
     délais
    1.02
    ではない
    1.02
    തില്‍
    1.02
    Activations Density 0.003%

    No Known Activations