© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11898
    Prev
    Next
    INDEX
    Explanations

    acyclovir, blisters, nitroglycerin, simplex

    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
     référence
    0.59
    ον
    0.51
    ліка
    0.51
     loc
    0.50
     sociologist
    0.50
    മ്പ്
    0.50
    ኻ
    0.49
    ění
    0.48
     earthquake
    0.47
    ชื่อ
    0.47
    POSITIVE LOGITS
    D
    0.59
     تضم
    0.58
    them
    0.53
     Pfizer
    0.52
    满意
    0.52
     اقد
    0.52
    قدر
    0.50
     Cedric
    0.50
    Q
    0.50
    تهم
    0.48
    Activations Density 0.005%

    No Known Activations