© 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. 118449
    Prev
    Next
    INDEX
    Explanations

    Year, month, day separators

    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
    inded
    0.35
     correspondiente
    0.33
     inflatable
    0.32
     setIsLoading
    0.32
     tasted
    0.31
     indonesia
    0.31
    flatable
    0.31
    韩
    0.31
     രണ്ടു
    0.30
     summarised
    0.30
    POSITIVE LOGITS
     సామ
    0.31
     flott
    0.31
    備
    0.31
    OP
    0.31
    RA
    0.30
     بها
    0.30
     ברי
    0.30
    preco
    0.30
     OP
    0.29
     ra
    0.29
    Activations Density 0.001%

    No Known Activations