© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8303
    Prev
    Next
    INDEX
    Explanations

    C++ code related to Boost unit tests and string manipulation, potentially involving tuples and matchers.

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     كومونز
    -1.13
     незавершена
    -1.10
     Roskov
    -1.02
     مرئيه
    -0.94
     Савезне
    -0.92
     doInBackground
    -0.92
     فريبيس
    -0.91
    HtmlAttribute
    -0.91
     дописавши
    -0.90
     الحره
    -0.89
    POSITIVE LOGITS
    ↵
    0.72
    <code>
    0.64
    <em>
    0.64
    <strong>
    0.62
    </strong>
    0.61
     
    0.61
    ',
    0.60
    ↵↵
    0.60
    ",
    0.53
    '
    0.52
    Activations Density 3.378%

    No Known Activations