© 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. 2701
    Prev
    Next
    INDEX
    Explanations

    a wide variety of technical and scientific terms

    oai_token-act-pair · 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
     Vikipedi
    -0.66
     ervan
    -0.56
    ribune
    -0.54
     justifyContent
    -0.52
     disambiguazione
    -0.51
    Varint
    -0.50
    GeV
    -0.50
    zyż
    -0.49
    SuppressLint
    -0.49
    tagHelper
    -0.49
    POSITIVE LOGITS
    :✨
    0.69
    WriteTagHelper
    0.69
    TagMode
    0.68
    <bos>
    0.65
    aarrggbb
    0.65
    SourceChecksum
    0.62
    atguigu
    0.61
    RefNanny
    0.56
    ThroughAttribute
    0.56
     समीक्षाओं
    0.55
    Activations Density 10.310%

    No Known Activations