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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14409
    Prev
    Next
    INDEX
    Explanations

    capital letters or compound words/phrases that often appear in scientific or medical literature.

    oai_token-act-pair · gemini-2.0-flash

    scientific text, formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    IsContent
    -0.68
     BoxDecoration
    -0.55
    jspx
    -0.52
    ftagPool
    -0.49
    aarrggbb
    -0.48
     ComVisible
    -0.48
    ValueStyle
    -0.47
    SpringBootTest
    -0.47
     HttpNotFound
    -0.47
    addCriterion
    -0.44
    POSITIVE LOGITS
     aDecoder
    0.57
     Noct
    0.56
    limiter
    0.53
    CppCodeGen
    0.53
     Diony
    0.52
     Agre
    0.52
    */].
    0.50
    liosis
    0.50
     OFDb
    0.49
    verifyException
    0.49
    Activations Density 0.493%

    No Known Activations