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. 992
    Prev
    Next
    INDEX
    Explanations

    words and symbols in software code, mathematics, or formal writing

    oai_token-act-pair · gemini-2.0-flash

    spatial

    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
     helicópter
    -0.50
     pájaros
    -0.49
     legal
    -0.46
    Transkript
    -0.46
    atyana
    -0.44
    帖最后由
    -0.44
     êtes
    -0.43
    beeld
    -0.43
    LookAnd
    -0.43
     person
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.70
    localctx
    0.69
    __":
    0.68
     Infórmanos
    0.67
    TagMode
    0.67
    __":
    
    0.66
     initComponents
    0.65
    __':
    
    0.61
    __':
    0.60
    makeText
    0.60
    Activations Density 7.891%

    No Known Activations