© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27891
    Prev
    Next
    INDEX
    Explanations

    start of code or documentation blocks

    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_40_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
     Shenzhen
    0.78
    深圳
    0.67
    广东省
    0.67
    莞
    0.66
     Guangdong
    0.64
    深圳市
    0.63
    粤
    0.60
    汕
    0.58
    Shen
    0.57
    滘
    0.56
    POSITIVE LOGITS
     Michigan
    0.47
    Michigan
    0.41
     MICHIGAN
    0.38
    IActionResult
    0.37
    يروس
    0.37
    Iowa
    0.36
     Lombok
    0.36
     hypothesis
    0.35
     станови
    0.35
    ╁
    0.35
    Activations Density 0.005%

    No Known Activations