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. 1203
    Prev
    Next
    INDEX
    Explanations

    words relating to health, diet, and nutrition, especially in connection with tea

    oai_token-act-pair · gemini-2.0-flash

    beverages

    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
     متعلقه
    -0.59
    ionView
    -0.53
    νή
    -0.53
    endsection
    -0.52
    jScrollPane
    -0.51
     nakalista
    -0.51
    autoconfigure
    -0.48
    dataProvider
    -0.47
     snippetHide
    -0.46
     intake
    -0.46
    POSITIVE LOGITS
     lenker
    0.54
    出版年
    0.53
    wijs
    0.53
    TemporalType
    0.52
     väli
    0.49
    ALSE
    0.48
    CodeAttribute
    0.48
     CreateTagHelper
    0.46
    を押
    0.45
     gevolg
    0.45
    Activations Density 12.000%

    No Known Activations