© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15234
    Prev
    Next
    INDEX
    Explanations

    instances of the word `load` co-occuring with terms related to webpages, javascript and scrolling.

    oai_token-act-pair · gemini-2.0-flash

    loading

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    出版年
    -0.61
    ActionCreators
    -0.54
    曖昧さ回避
    -0.53
    нительно
    -0.49
    alpin
    -0.47
     antichi
    -0.46
     burbuja
    -0.45
    createStatement
    -0.44
    ThroughAttribute
    -0.44
    quartered
    -0.44
    POSITIVE LOGITS
     loading
    1.35
     load
    1.21
     loaded
    1.19
     Loading
    1.16
     LOAD
    1.13
     LOADING
    1.13
     Load
    1.12
     Loads
    1.04
     loads
    1.04
    load
    1.04
    Activations Density 1.730%

    No Known Activations