Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2275
    Prev
    Next
    INDEX
    Explanations

    JSON code and XML markup tags

    oai_token-act-pair · gemini-2.0-flash

    Code-related content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.88
     myſelf
    -0.88
     againſt
    -0.83
     AssemblyProduct
    -0.83
     Efq
    -0.82
     themſelves
    -0.82
     himſelf
    -0.80
     raiſ
    -0.79
     doubtnut
    -0.79
     itſelf
    -0.79
    POSITIVE LOGITS
    landa
    0.61
    console
    0.50
    sten
    0.49
    :'#
    0.49
    #\
    0.48
    tw
    0.47
     $
    0.47
    tre
    0.46
     #
    0.46
    end
    0.46
    Activations Density 2.162%

    No Known Activations