© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91103
    Prev
    Next
    INDEX
    Explanations

    Personal Protective Equipment (PPE)

    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_3_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
    m
    0.69
     ເ
    0.61
    r
    0.59
    ﮈ
    0.57
    एम
    0.55
     vreme
    0.53
    ﺭ
    0.53
    meyi
    0.52
     jî
    0.52
    爲
    0.52
    POSITIVE LOGITS
    ی
    0.90
    د
    0.89
    ب
    0.89
    ك
    0.84
    ים
    0.82
    schutz
    0.81
    ों
    0.79
    ка
    0.79
    д
    0.78
    ص
    0.78
    Activations Density 0.001%

    No Known Activations