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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16316
    Prev
    Next
    INDEX
    Explanations

    patterns from emails and blog posts including forwarding, publishing dates, and thoughts

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
     so
    -0.50
     me
    -0.46
     touch
    -0.46
    featureID
    -0.43
     –
    -0.40
    callable
    -0.38
     st
    -0.37
     推荐
    -0.37
     Erişim
    -0.37
    éric
    -0.37
    POSITIVE LOGITS
     themſelves
    0.93
     itſelf
    0.92
     مشين
    0.89
     Efq
    0.88
     himſelf
    0.85
     poffe
    0.84
     myſelf
    0.81
     defaultstate
    0.79
     leſs
    0.78
     houſe
    0.77
    Activations Density 0.824%

    No Known Activations