© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197319
    Prev
    Next
    INDEX
    Explanations

    Hadrian, Adriano, Domitian emperors

    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_15_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
     Vocational
    0.51
    ২০
    0.49
    剜
    0.48
     Sanitation
    0.47
    se
    0.47
    Voc
    0.47
    Literatura
    0.46
    ienen
    0.46
     الحكومة
    0.45
    _{
    0.44
    POSITIVE LOGITS
     Kita
    0.55
     atras
    0.49
     красиво
    0.49
     dihedral
    0.47
     Jill
    0.47
     ("",
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    出来る
    0.46
     살펴
    0.45
     красивая
    0.45
    Activations Density 0.001%

    No Known Activations