© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195482
    Prev
    Next
    INDEX
    Explanations

    cryptography and science

    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_4_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
    ف
    1.42
    for
    1.22
     for
    1.19
    and
    1.19
     on
    1.05
     as
    1.00
     samoch
    0.97
     an
    0.92
    IR
    0.90
     primeiro
    0.89
    POSITIVE LOGITS
    로
    0.93
    (
    0.85
    с
    0.84
    al
    0.82
    g
    0.80
    ও
    0.78
    は
    0.77
    "}}
    0.73
    Архівовано
    0.72
    .(
    0.71
    Activations Density 0.002%

    No Known Activations