© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208321
    Prev
    Next
    INDEX
    Explanations

    static declarations

    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_20_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
     얘가
    0.31
    Bathroom
    0.31
     tamam
    0.31
    .}(
    0.30
    Ком
    0.30
    вають
    0.30
    Nope
    0.30
    Jumlah
    0.30
     kayu
    0.29
     TeV
    0.29
    POSITIVE LOGITS
    ス
    0.33
    с
    0.32
    Prints
    0.31
    ِل
    0.29
    ס
    0.29
     প্র
    0.29
    ks
    0.29
    ч
    0.29
    LINE
    0.28
    ERIC
    0.28
    Activations Density 0.001%

    No Known Activations