© 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. 1774
    Prev
    Next
    INDEX
    Explanations

    structured data, potentially in tables or lists, with a focus on code snippets or data records, possibly related to medical or legal contexts

    oai_token-act-pair · gemini-2.0-flash

    html table rows

    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
    
    -0.65
    queryInterface
    -0.52
    /*++
    -0.48
    fromnode
    -0.47
    URLException
    -0.46
    DrawerLayout
    -0.45
    olá
    -0.44
     /\.(
    -0.43
     SPDX
    -0.43
     ModelExpression
    -0.43
    POSITIVE LOGITS
    Хьажоргаш
    0.66
    engertian
    0.64
     >=",
    0.63
     विश्वसनीयता
    0.61
    elemField
    0.61
    ագրություններ
    0.60
    usiai
    0.59
    mybatisplus
    0.58
    ViewImports
    0.57
     réduite
    0.57
    Activations Density 2.242%

    No Known Activations