© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81860
    Prev
    Next
    INDEX
    Explanations

    roles and people

    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_53_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
    领
    0.73
    領
    0.70
     지도
    0.67
     dirige
    0.62
     lider
    0.58
     conduc
    0.57
    指導
    0.57
    领导
    0.55
     gobern
    0.55
     ஆட்சிய
    0.55
    POSITIVE LOGITS
    ссор
    0.37
     அல
    0.36
     تیل
    0.36
     contr
    0.35
     উঠলো
    0.35
    嗔
    0.35
    業
    0.34
     испол
    0.33
     coups
    0.33
     migliore
    0.33
    Activations Density 0.002%

    No Known Activations