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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8651
    Prev
    Next
    INDEX
    Explanations

    code referring to a request object, getting data from the request

    oai_token-act-pair · gemini-2.0-flash

    request

    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
    request
    -1.05
     request
    -0.69
    Request
    -0.63
     Request
    -0.60
    featureID
    -0.60
     nawr
    -0.58
     CommonModule
    -0.58
    TypedDataSet
    -0.55
     AspNetCore
    -0.55
    parsedMessage
    -0.54
    POSITIVE LOGITS
    ंदीखरीदारी
    0.73
    帖最后由
    0.58
    Erreferentziak
    0.56
    codable
    0.56
     prepaid
    0.55
    trine
    0.53
    stuk
    0.53
     intermédiaire
    0.51
    complexType
    0.51
    بوابة
    0.51
    Activations Density 0.188%

    No Known Activations