© 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. 45089
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    :
    0.72
     autrefois
    0.69
    ?
    0.66
     essentiel
    0.64
    ä
    0.64
    (
    0.63
     étaient
    0.62
    (|
    0.62
     o
    0.60
     uygun
    0.60
    POSITIVE LOGITS
    r
    0.95
    on
    0.87
    a
    0.79
    the
    0.79
    رود
    0.79
    ر
    0.75
    。「
    0.75
    ется
    0.73
    ।’
    0.71
    세요
    0.71
    Activations Density 0.000%

    No Known Activations