© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6247
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, specifically related to APIs, database queries, and class structures

    oai_token-act-pair · gemini-2.0-flash

    code/project organization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Roskov
    -0.72
     lenker
    -0.62
     Backing
    -0.56
     autorytatywna
    -0.52
    setVerticalGroup
    -0.50
    TRIBUN
    -0.49
    はじめに
    -0.49
    BufferException
    -0.49
    Външни
    -0.49
     ligiloj
    -0.45
    POSITIVE LOGITS
    expandindo
    0.77
    <bos>
    0.68
     télévis
    0.59
    HideFlags
    0.58
     blanches
    0.58
     honom
    0.57
     mør
    0.57
     mourut
    0.57
     artificiales
    0.57
     zijne
    0.56
    Activations Density 10.286%

    No Known Activations