© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149405
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    s
    0.88
    ਆਂ
    0.47
    ی
    0.47
    ",
    0.46
    ים
    0.45
    ³,
    0.44
    ের
    0.44
    sPath
    0.43
    sede
    0.43
    a
    0.42
    POSITIVE LOGITS
     العمر
    0.57
    Age
    0.55
     Age
    0.55
    Where
    0.52
    Time
    0.49
    To
    0.49
    WHERE
    0.48
    Century
    0.47
    Edad
    0.47
    Winter
    0.47
    Activations Density 0.001%

    No Known Activations