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. 1735
    Prev
    Next
    INDEX
    Explanations

    language about social justice issues and marginalized groups

    oai_token-act-pair · gemini-2.0-flash

    broad social, academic discussions

    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
    TagHelper
    -0.65
    Carriera
    -0.57
    RTLD
    -0.57
    grids
    -0.56
    HasForeignKey
    -0.56
    FontOfSize
    -0.56
    SEGUIR
    -0.53
    GenerationType
    -0.50
    oltre
    -0.49
    geme
    -0.49
    POSITIVE LOGITS
     незавершена
    0.54
     betweenstory
    0.51
    fjspx
    0.49
    jsoup
    0.48
     propOrder
    0.47
    expandindo
    0.47
     smtplib
    0.46
    BlockingQueue
    0.46
    PRNewswire
    0.46
    uyler
    0.45
    Activations Density 13.809%

    No Known Activations