© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1656
    Prev
    Next
    INDEX
    Explanations

    boilerplate language used to describe figures and inventions in patents or technical documents

    oai_token-act-pair · gemini-2.0-flash

    fabric

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IsMutable
    -0.52
    roppo
    -0.50
    ']")
    -0.49
    onsored
    -0.49
    GeneratedMessage
    -0.48
    buttonBar
    -0.48
     cucchiai
    -0.48
    webElementXpaths
    -0.48
    Chú
    -0.47
     rhestr
    -0.45
    POSITIVE LOGITS
     fabric
    1.44
    fabric
    1.10
     Fabric
    1.09
     FABRIC
    0.94
    Fabric
    0.92
     fabrics
    0.83
    FABRIC
    0.80
     ویکی‌پدیا
    0.63
     Fabrics
    0.61
     cloth
    0.59
    Activations Density 4.857%

    No Known Activations