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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 733
    Prev
    Next
    INDEX
    Explanations

    technical terms typically found in scientific reports and experimental descriptions

    oai_token-act-pair · gemini-2.0-flash

    chemical compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     chemistry
    -0.65
     chemists
    -0.63
     chemicals
    -0.61
     tasted
    -0.60
     tasting
    -0.60
     substances
    -0.60
     chemical
    -0.59
    Taste
    -0.58
     Taste
    -0.57
     chimique
    -0.57
    POSITIVE LOGITS
     >=",
    0.58
    StoryboardSegue
    0.52
    hörigen
    0.51
    __);
    0.50
    )++;
    0.47
    DOCTYPE
    0.47
     AssemblyCompany
    0.47
    Izvori
    0.46
    Cancel
    0.46
    Begriffsklä
    0.46
    Activations Density 2.973%

    No Known Activations