© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134508
    Prev
    Next
    INDEX
    Explanations

    pygame.display.set_caption

    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
    s
    1.30
    ك
    1.09
    p
    1.00
    س
    0.97
    с
    0.96
    ের
    0.91
    g
    0.88
    މ
    0.88
    л
    0.88
    स
    0.86
    POSITIVE LOGITS
     没有
    0.77
     číslo
    0.77
     我們
    0.75
     联系
    0.73
     沒有
    0.73
    ong
    0.72
    。</
    0.71
     类型
    0.70
    ani
    0.70
     项目
    0.69
    Activations Density 0.002%

    No Known Activations