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. 14343
    Prev
    Next
    INDEX
    Explanations

    words that indicate lists or opinions being provided.

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     ExecuteAsync
    -0.74
     >=",
    -0.72
    ViewFeatures
    -0.70
     PhpStorm
    -0.69
    ."]
    -0.68
     Wikispecies
    -0.68
    ?")
    -0.66
    saraba
    -0.66
    COUVER
    -0.65
    
    -0.64
    POSITIVE LOGITS
     réguli
    0.62
     Your
    0.59
     There
    0.59
     It
    0.57
     Their
    0.53
     rocas
    0.50
     Everything
    0.50
     so
    0.50
     Its
    0.50
     Other
    0.49
    Activations Density 0.947%

    No Known Activations