© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131953
    Prev
    Next
    INDEX
    Explanations

    function name definition

    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_1_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
    2
    1.16
    Z
    1.07
    H
    1.06
    0.98
    L
    0.91
    S
    0.88
    B
    0.85
    /
    0.83
    K
    0.82
    M
    0.81
    POSITIVE LOGITS
    н
    0.96
     in
    0.91
    א
    0.88
    น
    0.84
    é
    0.82
    ン
    0.80
     пациентов
    0.79
     integrate
    0.78
     américains
    0.78
    𝑙
    0.77
    Activations Density 0.043%

    No Known Activations