© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63105
    Prev
    Next
    INDEX
    Explanations

    trauma injury

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     трав
    1.15
    Injury
    1.09
     injury
    1.07
     Injury
    1.07
    injury
    0.96
     Injuries
    0.90
     injuries
    0.88
    伤
    0.79
    傷
    0.78
     тра
    0.72
    POSITIVE LOGITS
     head
    1.51
    head
    1.16
     Head
    1.14
    Head
    1.11
     ch
    1.05
     HEAD
    0.91
    ヘッド
    0.85
    HEAD
    0.84
     हेड
    0.83
    т
    0.80
    Activations Density 0.001%

    No Known Activations