© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118235
    Prev
    Next
    INDEX
    Explanations

    device type ('tv', 'mobile')

    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_27_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
    参考文献
    0.49
     Beek
    0.45
    炁
    0.44
     Photographic
    0.43
    焲
    0.43
     Librarian
    0.43
     Literature
    0.42
    仴
    0.42
     Recursive
    0.42
     letteratura
    0.42
    POSITIVE LOGITS
     odor
    0.40
     naprav
    0.40
     arabic
    0.39
     customer
    0.39
    anation
    0.39
     army
    0.39
     rhino
    0.39
     ople
    0.38
    Saudi
    0.38
    नर
    0.38
    Activations Density 0.047%

    No Known Activations