© 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. 35975
    Prev
    Next
    INDEX
    Explanations

    sort algorithm, obesity, law

    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
    ate
    0.71
    ‌است
    0.71
    ی
    0.66
    em
    0.65
    ে
    0.62
    emort
    0.61
    ın
    0.61
    ний
    0.61
    IN
    0.58
    وای
    0.58
    POSITIVE LOGITS
     přid
    0.73
     étapes
    0.67
     ergän
    0.66
     إضافة
    0.66
     Eats
    0.66
    to
    0.64
     agregó
    0.63
     satisfacción
    0.63
     otáz
    0.63
    {
    0.61
    Activations Density 0.008%

    No Known Activations