© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59937
    Prev
    Next
    INDEX
    Explanations

    partial or partially

    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_11_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
    on
    0.76
    et
    0.75
    س
    0.71
    it
    0.70
    t
    0.68
    B
    0.66
     scorer
    0.65
    j
    0.65
    V
    0.65
    Р
    0.63
    POSITIVE LOGITS
    ほとんど
    0.66
    기
    0.60
    𝗱
    0.60
    بری
    0.59
     Thực
    0.59
    𝚢
    0.59
    はじめ
    0.59
    ジェクト
    0.58
    𝗸
    0.57
    by
    0.57
    Activations Density 0.000%

    No Known Activations