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. 1687
    Prev
    Next
    INDEX
    Explanations

    words when describing olive oil production

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
    WebVitals
    -0.56
    InSection
    -0.53
    PCell
    -0.50
     Thore
    -0.50
    StrictMode
    -0.48
    klis
    -0.47
     AssemblyCompany
    -0.47
    extAlignment
    -0.46
     userSchema
    -0.46
    createClass
    -0.46
    POSITIVE LOGITS
     محفوظة
    0.76
     الاطلاع
    0.71
     lenker
    0.65
    تقاوى
    0.62
     ivelany
    0.61
     يتيمه
    0.60
    MLLoader
    0.59
    richTextPanel
    0.59
    OGND
    0.58
     pageContext
    0.57
    Activations Density 11.972%

    No Known Activations