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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10292
    Prev
    Next
    INDEX
    Explanations

    various function words such as prepositions and conjunctions, along with discourse markers and adjectives.

    oai_token-act-pair · gemini-2.0-flash

    economic development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    opardy
    -0.52
     Abar
    -0.48
     reich
    -0.47
     anhyd
    -0.47
    AutoresizingMask
    -0.47
    KEYCODE
    -0.47
    scrapy
    -0.47
     Badge
    -0.46
    avadoc
    -0.46
     austral
    -0.45
    POSITIVE LOGITS
    MigrationBuilder
    0.68
    IUrlHelper
    0.63
     growth
    0.63
     AssemblyTitle
    0.61
    __;
    0.60
     lenker
    0.60
     ostavi
    0.59
     Growth
    0.58
    󠁴
    0.56
     ویکی‌پدی
    0.56
    Activations Density 2.920%

    No Known Activations