© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148805
    Prev
    Next
    INDEX
    Explanations

    code dataframes

    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_59_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
    '+
    0.42
    []
    0.41
     danych
    0.40
     naszych
    0.39
    [$
    0.39
     самых
    0.38
    []=
    0.38
     delle
    0.38
     Các
    0.37
    ',$
    0.36
    POSITIVE LOGITS
     (“
    0.47
    to
    0.46
    !!)
    0.46
     ("
    0.46
    ("/"))
    0.45
    ("-
    0.45
     (-
    0.44
    still
    0.44
    into
    0.44
    ("
    0.44
    Activations Density 0.002%

    No Known Activations