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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6936
    Prev
    Next
    INDEX
    Explanations

    words related to orders, deliveries, and auctions

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hochspringen
    -0.88
     Мексичка
    -0.85
    EndGlobalSection
    -0.77
     دیکھیے
    -0.75
    +:+
    -0.73
    enderror
    -0.70
     onAnimation
    -0.68
    kháu
    -0.68
     незавершена
    -0.66
    Hauptartikel
    -0.66
    POSITIVE LOGITS
    itel
    0.41
    Fix
    0.40
    ционная
    0.38
     pove
    0.37
    IContainer
    0.36
    <blockquote>
    0.35
    цион
    0.35
    idjan
    0.34
    傾向
    0.34
    ционный
    0.34
    Activations Density 3.396%

    No Known Activations