© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5800
    Prev
    Next
    INDEX
    Explanations

    the word "url"

    oai_token-act-pair · gemini-2.0-flash

    url

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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>
    -1.13
     helplessly
    -0.65
     Efq
    -0.63
    4
    -0.63
    <h3>
    -0.63
    7
    -0.61
     😭😭
    -0.61
    "
    -0.60
     disgra
    -0.60
    <h2>
    -0.59
    POSITIVE LOGITS
     fédé
    0.78
     médicaux
    0.75
    |','
    0.74
     commerciaux
    0.73
    ScopeManager
    0.72
     auroit
    0.69
     lautet
    0.68
    setVerticalGroup
    0.66
     InputDecoration
    0.65
    hezza
    0.65
    Activations Density 0.524%

    No Known Activations