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. 14852
    Prev
    Next
    INDEX
    Explanations

    punctuation, conjunctions, and discourse markers

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     StatelessWidget
    -0.63
    PRNewswire
    -0.59
    fml
    -0.56
     %>%
    -0.52
     orchids
    -0.52
     OMIT
    -0.50
    さつ
    -0.49
     useCallback
    -0.49
     rise
    -0.49
    躇
    -0.49
    POSITIVE LOGITS
     initComponents
    0.82
    ValueStyle
    0.64
     &___
    0.60
    Искәрмәләр
    0.60
    ftagPool
    0.59
     CreateTagHelper
    0.58
     ujednoznacz
    0.58
    copg
    0.57
    ագրություններ
    0.56
     disambiguazione
    0.56
    Activations Density 2.585%

    No Known Activations