© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11535
    Prev
    Next
    INDEX
    Explanations

    varieties and compression

    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_13_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
    ک
    0.50
    ﺑ
    0.43
    ক
    0.43
    γ
    0.42
    インスト
    0.41
    க
    0.41
     செல்சிய
    0.40
    arnya
    0.40
     khel
    0.40
    МІ
    0.40
    POSITIVE LOGITS
    ivo
    0.45
     gene
    0.41
    javaHome
    0.41
     적
    0.40
    clonal
    0.40
    io
    0.40
    Compile
    0.40
    ,...
    0.40
    MapView
    0.40
    ಮಾಡ
    0.40
    Activations Density 0.030%

    No Known Activations