© 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. 196614
    Prev
    Next
    INDEX
    Explanations

    working to improve

    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
     Chinook
    0.43
     sozinho
    0.41
     Walmart
    0.40
     शासकीय
    0.39
     красивые
    0.39
     a
    0.39
    ir
    0.38
     красиво
    0.38
     sozinha
    0.38
     நடக்க
    0.38
    POSITIVE LOGITS
     accountNumber
    0.41
     thing
    0.40
     ευρώ
    0.40
    ែម
    0.39
     attribut
    0.37
    Penumpang
    0.36
     refinement
    0.35
    丟
    0.35
     deletion
    0.35
    Intercept
    0.35
    Activations Density 0.002%

    No Known Activations