© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157542
    Prev
    Next
    INDEX
    Explanations

    worsening

    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_2_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
     for
    1.92
    s
    1.73
    4
    1.39
    5
    1.36
     you
    1.34
    ים
    1.31
    ه
    1.30
    im
    1.28
    ur
    1.27
    8
    1.27
    POSITIVE LOGITS
    的技术
    1.13
    ependent
    1.08
    <0x91>
    1.05
     följande
    1.05
    的游戏
    0.97
    的分
    0.95
     và
    0.95
    的设计
    0.94
    chließlich
    0.93
    <0x96>
    0.92
    Activations Density 0.000%

    No Known Activations