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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7239
    Prev
    Next
    INDEX
    Explanations

    curly brackets indicating code blocks

    oai_token-act-pair · gemini-2.0-flash

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     }}$}
    -0.91
     Diſ
    -0.91
     ſtate
    -0.90
     purpoſe
    -0.88
    "]
    
    -0.87
     ftate
    -0.86
     ſch
    -0.84
    __(/*!
    -0.83
    ".
    
    -0.83
     ſeveral
    -0.82
    POSITIVE LOGITS
    <bos>
    1.32
    ↵↵
    0.84
    ↵
    0.63
    [
    0.60
    ’
    0.59
    mybatisplus
    0.56
    /
    0.54
     kasarigan
    0.52
    https
    0.50
    -
    0.48
    Activations Density 0.766%

    No Known Activations