© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42516
    Prev
    Next
    INDEX
    Explanations

    Te, tea, teapot, Te Papa, Lasso

    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_3_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
    '
    1.03
     uptick
    0.62
    /
    0.62
    -
    0.61
     to
    0.59
    ка
    0.56
     cruising
    0.55
     hustle
    0.55
    va
    0.55
     scrap
    0.55
    POSITIVE LOGITS
    ס
    0.81
    리
    0.70
    ها
    0.68
    سازی
    0.68
     চিকিৎ
    0.66
    ের
    0.66
    getType
    0.66
    س
    0.64
    ስ
    0.64
    submit
    0.63
    Activations Density 0.011%

    No Known Activations