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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13684
    Prev
    Next
    INDEX
    Explanations

    chemical formulas, molecules and processes, or things related to chemistry.

    oai_token-act-pair · gemini-2.0-flash

    carbon dioxide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     всему
    -0.50
    Ссылки
    -0.50
     szab
    -0.49
    fetchone
    -0.48
     mét
    -0.48
    borderTop
    -0.47
     double
    -0.47
    ánky
    -0.47
    UTION
    -0.46
    reactstrap
    -0.46
    POSITIVE LOGITS
    出版年
    0.74
    RegistryLite
    0.66
     gas
    0.65
     Syrie
    0.65
    InjectAttribute
    0.64
    ftagPool
    0.63
     boto
    0.62
     Viber
    0.62
     monoxide
    0.62
    новниш
    0.62
    Activations Density 1.100%

    No Known Activations