© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1879
    Prev
    Next
    INDEX
    Explanations

    the word "request" in code

    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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -2.34
    request
    -2.27
    Request
    -2.19
     Request
    -2.14
     requests
    -1.97
     Requests
    -1.84
     REQUEST
    -1.77
     requesting
    -1.75
    REQUEST
    -1.66
     requested
    -1.66
    POSITIVE LOGITS
    Hauptartikel
    0.68
    disambiguation
    0.61
    ReusableCell
    0.58
    ArgsConstructor
    0.54
    ähig
    0.52
     initComponents
    0.52
    !*\
    0.51
     doInBackground
    0.50
    kuuta
    0.50
    pulumi
    0.50
    Activations Density 1.248%

    No Known Activations