© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131783
    Prev
    Next
    INDEX
    Explanations

    Di-

    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_6_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
    的气
    0.98
     dará
    0.97
    的状态
    0.95
     ν
    0.93
    的确
    0.92
    的变化
    0.92
    ’;
    0.92
    та
    0.90
    的能力
    0.90
    的操作
    0.89
    POSITIVE LOGITS
    in
    1.80
    a
    1.68
    t
    1.61
    f
    1.60
    g
    1.59
    c
    1.57
    de
    1.49
    n
    1.45
    ni
    1.40
    ad
    1.39
    Activations Density 0.001%

    No Known Activations