© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6041
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables and results, especially in academic papers

    oai_token-act-pair · gemini-2.0-flash

    data presentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    UserScript
    -1.05
     فريبيس
    -0.88
     متعلقه
    -0.87
    InputBorder
    -0.85
     Мексичка
    -0.83
    Tikang
    -0.80
    TintMode
    -0.80
     Monfieur
    -0.79
     bezeichneter
    -0.79
     eventdata
    -0.78
    POSITIVE LOGITS
    .
    0.66
     
    0.63
    <strong>
    0.57
    ​
    0.53
    <b>
    0.50
    "
    0.50
    <em>
    0.48
     A
    0.48
    to
    0.48
    ↵
    0.47
    Activations Density 1.695%

    No Known Activations