© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10163
    Prev
    Next
    INDEX
    Explanations

    markers of documents and document structure

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -0.94
     typelib
    -0.88
    '])
    -0.80
     Biôgrafia
    -0.80
    '))
    -0.78
     الرياضيه
    -0.78
    ChildScrollView
    -0.77
    ']").
    -0.76
    +:+
    -0.75
     Мексичка
    -0.75
    POSITIVE LOGITS
     geloof
    0.55
     aéreo
    0.52
     coscienza
    0.51
     mennesker
    0.50
     kolye
    0.49
     giustizia
    0.48
    konomi
    0.47
     yayınları
    0.47
     hırka
    0.46
     arvio
    0.44
    Activations Density 2.522%

    No Known Activations