© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17566
    Prev
    Next
    INDEX
    Explanations

    Donald Trump

    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_34_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
    出道
    0.39
     cháy
    0.36
     evolutionary
    0.36
    មូល
    0.35
    부를
    0.33
     خدم
    0.33
     الاحت
    0.33
    ../../
    0.33
     MILK
    0.33
    measurable
    0.33
    POSITIVE LOGITS
     Trump
    0.87
    Trump
    0.86
     Donald
    0.79
    特朗普
    0.77
    Donald
    0.71
     ट्रंप
    0.70
     डोनाल्ड
    0.59
    trump
    0.55
    donald
    0.53
     প্রেসিডেন্টের
    0.52
    Activations Density 0.018%

    No Known Activations