© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13359
    Prev
    Next
    INDEX
    Explanations

    code related to parsing HTTP headers, particularly "content-type"

    oai_token-act-pair · gemini-2.0-flash

    HTTP headers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    archiviato
    -0.59
     ویکی‌پدیا
    -0.45
    WriteLiteral
    -0.45
    zina
    -0.43
     مرئيه
    -0.43
     Colleges
    -0.43
     hydroxide
    -0.43
    GIVEREF
    -0.43
    igate
    -0.42
    CreateModel
    -0.42
    POSITIVE LOGITS
    WithIOException
    0.78
    MessageTagHelper
    0.74
    Lähteet
    0.70
     متعلقه
    0.64
    */),
    0.61
    openConnection
    0.58
     esternos
    0.57
    ofire
    0.57
     ivelany
    0.57
    >−
    0.56
    Activations Density 0.916%

    No Known Activations