© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12532
    Prev
    Next
    INDEX
    Explanations

    text from scientific research papers, including citations, dataset names, and specific terminology from biology, archaeology, and computer science.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     otomatig
    -0.65
     cref
    -0.59
    makeText
    -0.58
    forName
    -0.57
    liferay
    -0.52
    ofType
    -0.52
    textTheme
    -0.50
     loadImage
    -0.49
    Erstellt
    -0.48
     onOptions
    -0.48
    POSITIVE LOGITS
    Transkript
    0.63
    তথ্যসূত্র
    0.53
     كومونز
    0.50
    ();)
    0.50
     nakalista
    0.48
     године
    0.47
    contentLoaded
    0.47
    tagHelperRunner
    0.47
    وصلات
    0.47
     متحده
    0.46
    Activations Density 7.862%

    No Known Activations