© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138483
    Prev
    Next
    INDEX
    Explanations

    CPU execution and control flow

    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_12_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
    cession
    0.58
     উচ্চারণ
    0.56
     disediakan
    0.54
    брать
    0.53
    unov
    0.53
     orchestrated
    0.52
    imam
    0.52
    w
    0.52
     উচ্চার
    0.51
    chaoxing
    0.50
    POSITIVE LOGITS
    Ｉ
    0.59
     ใน
    0.54
    𝙻
    0.54
    𝙇
    0.53
    𝙈
    0.51
    𝙸
    0.50
     गड
    0.50
     I
    0.50
     홍
    0.50
    误差
    0.50
    Activations Density 0.008%

    No Known Activations