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. 827
    Prev
    Next
    INDEX
    Explanations

    Swift code related to UITableViewCells and data population

    oai_token-act-pair · gemini-2.0-flash

    cell

    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
    :");
    -0.55
    ?',
    -0.53
    ?”.
    -0.53
    piac
    -0.52
    ');
    
    -0.51
     BoxDecoration
    -0.51
    Bronnen
    -0.51
    :])
    -0.50
    (");
    -0.50
     ويكيميديا
    -0.49
    POSITIVE LOGITS
     ISNI
    0.66
    BarStyle
    0.56
    ItemBackground
    0.53
     Paglinawan
    0.50
    MLLoader
    0.49
     smtplib
    0.48
    __*/
    0.48
    AutoScaleMode
    0.48
     PLWABN
    0.47
    出版
    0.47
    Activations Density 25.566%

    No Known Activations