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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16327
    Prev
    Next
    INDEX
    Explanations

    a mess of contexts containing possessives, periods related to chronology, small verbs, and sports contexts.

    oai_token-act-pair · gemini-2.0-flash

    beginnings or introductions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     start
    -1.05
     debut
    -1.00
     starts
    -0.98
     début
    -0.96
     started
    -0.94
     begun
    -0.93
     begins
    -0.93
     begin
    -0.91
     Start
    -0.90
     Started
    -0.88
    POSITIVE LOGITS
    ChildScrollView
    0.81
    Datuak
    0.77
    UserScript
    0.71
    extAlignment
    0.65
     UnityEditor
    0.64
    httphttps
    0.59
     WebDriverWait
    0.58
     ويكيميديا
    0.57
    তথ্যসূত্র
    0.57
    VideoCapture
    0.57
    Activations Density 1.247%

    No Known Activations