© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9293
    Prev
    Next
    INDEX
    Explanations

    substrings of computer code and scientific documents with unusual formatting

    oai_token-act-pair · gemini-2.0-flash

    hyphens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tvguidetime
    -1.01
    httphttps
    -0.76
    tanleria
    -0.73
     /\.
    -0.73
    ImageContext
    -0.72
    )";
    -0.72
     initComponents
    -0.72
    COUVER
    -0.72
     vuitton
    -0.72
     }}"
    -0.72
    POSITIVE LOGITS
    ArgumentParser
    0.41
     order
    0.39
     congi
    0.38
    pretation
    0.38
     Maß
    0.37
    밍
    0.37
     useEffect
    0.36
    <sup>
    0.36
    ceiling
    0.36
     entry
    0.36
    Activations Density 1.081%

    No Known Activations