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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1542
    Prev
    Next
    INDEX
    Explanations

    boiler plate copyright and licensing language

    oai_token-act-pair · gemini-2.0-flash

    Licenses and legal code

    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
    تقاوى
    -0.74
     Support
    -0.71
     Service
    -0.71
     Specific
    -0.71
     More
    -0.71
     Most
    -0.70
     Look
    -0.70
     Control
    -0.70
     Use
    -0.69
     Basic
    -0.69
    POSITIVE LOGITS
     Efq
    0.99
     Monfieur
    0.93
     myſelf
    0.88
     Shakspeare
    0.87
     pleaſure
    0.84
     avoient
    0.84
     Jefus
    0.83
     purpoſe
    0.80
     themſelves
    0.80
     himſelf
    0.80
    Activations Density 24.110%

    No Known Activations