© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15534
    Prev
    Next
    INDEX
    Explanations

    phrases related to client-server web communication, in particular, it looks for Javascript code making HTTP requests

    oai_token-act-pair · gemini-2.0-flash

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     resourceCulture
    -0.81
     ***!
    -0.70
     quæ
    -0.68
    matchCondition
    -0.67
    enumi
    -0.66
    +#+#
    -0.66
     congratulations
    -0.63
    WindowConstants
    -0.63
    IsContent
    -0.63
    findpost
    -0.62
    POSITIVE LOGITS
    SequentialGroup
    0.49
    Begriffsklä
    0.49
    GEBURTS
    0.47
    ofern
    0.47
    prüche
    0.46
    chaf
    0.45
    Finale
    0.45
    LabelTagHelper
    0.44
    iprot
    0.43
    ırken
    0.43
    Activations Density 56.825%

    No Known Activations