© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13483
    Prev
    Next
    INDEX
    Explanations

    terms related to software code, especially within the context of operating systems, drivers, or embedded systems

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    thâu
    -0.69
    HomeAsUpEnabled
    -0.64
     tartalomajánló
    -0.63
    RenderAtEndOf
    -0.62
    nonatomic
    -0.59
     typelib
    -0.55
    存于互联网档案馆
    -0.55
     HomeController
    -0.53
    webElementGuid
    -0.53
    oneph
    -0.53
    POSITIVE LOGITS
     ligiloj
    0.54
    ALLE
    0.50
     GeoNames
    0.49
    XmlAccessType
    0.49
    scrapy
    0.48
     مرئيه
    0.48
    хьтан
    0.47
    CodedInputStream
    0.47
    Hozzáférés
    0.46
    ibatis
    0.45
    Activations Density 1.985%

    No Known Activations