© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27277
    Prev
    Next
    INDEX
    Explanations

    code/data structures

    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_10_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
    .
    1.00
    n
    0.95
    '
    0.91
    W
    0.85
    ’
    0.82
    as
    0.82
     dotycz
    0.80
    an
    0.73
    M
    0.73
    ara
    0.71
    POSITIVE LOGITS
    л
    1.14
    ز
    0.73
     estão
    0.70
     řek
    0.67
     ে
    0.66
    мих
    0.65
    ترین
    0.64
    वर्ती
    0.64
    ó
    0.64
     اور
    0.63
    Activations Density 0.003%

    No Known Activations