© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3809
    Prev
    Next
    INDEX
    Explanations

    various programming language keywords, especially those related to importing libraries

    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_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     disambiguazione
    -0.71
    IUrlHelper
    -0.68
    تقاوى
    -0.67
    NameInMap
    -0.66
    abestanden
    -0.64
     autorytatywna
    -0.64
     transférez
    -0.63
    imageshack
    -0.61
     oprot
    -0.59
    </thead>
    -0.58
    POSITIVE LOGITS
    chtenstein
    0.56
    جغرافيا
    0.52
    risten
    0.49
     direta
    0.47
     spezif
    0.47
     Blackwood
    0.46
    karni
    0.46
     scoper
    0.46
     onCreateView
    0.46
     découvertes
    0.45
    Activations Density 0.957%

    No Known Activations