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. 10394
    Prev
    Next
    INDEX
    Explanations

    abbreviations, scientific terms, and acronyms with surrounding context like parentheses and colons

    oai_token-act-pair · gemini-2.0-flash

    Abbreviations and symbols

    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
    úsqueda
    -0.39
    mido
    -0.39
    ัต
    -0.38
    irsi
    -0.37
     DPS
    -0.37
    hdas
    -0.37
     storici
    -0.37
    gamos
    -0.36
    irte
    -0.36
    kowej
    -0.36
    POSITIVE LOGITS
    脚注の使い方
    1.13
    Geplaatst
    1.12
     CreateTagHelper
    1.09
     समीक्षाओं
    1.07
     disambiguazione
    1.02
     ویکی‌پدی
    1.00
    دانشنامهٔ
    0.98
     فريبيس
    0.96
     kaarangay
    0.93
     الرياضيه
    0.93
    Activations Density 8.468%

    No Known Activations