© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9233
    Prev
    Next
    INDEX
    Explanations

    physical harm or injury

    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_13_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
    H
    0.54
    </strong>
    0.50
     من
    0.48
     minum
    0.48
     traw
    0.47
    ikal
    0.47
    Squ
    0.46
    akal
    0.46
    Haw
    0.46
    from
    0.46
    POSITIVE LOGITS
    𝖘
    0.63
    皮肤
    0.56
    症状
    0.55
    );"
    0.54
    𝐬
    0.54
    бо
    0.54
    𝒔
    0.53
     específicas
    0.52
    ఎస్‌
    0.52
     lesión
    0.52
    Activations Density 0.069%

    No Known Activations