© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14855
    Prev
    Next
    INDEX
    Explanations

    references to hypothetical situations, customers, or projects and their relationship to a specific company

    oai_token-act-pair · gemini-2.0-flash

    countries, projects, companies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    }`).
    -0.61
    UpdateTime
    -0.55
    anhão
    -0.52
    openzeppelin
    -0.51
     EXPOSURE
    -0.50
     actionMode
    -0.50
     WARRANTIES
    -0.50
    makeConstraints
    -0.50
    bahar
    -0.49
    zzleHttp
    -0.49
    POSITIVE LOGITS
    unknownFields
    0.67
     CreateTagHelper
    0.59
     ویکی‌پدیا
    0.59
    FunctionFlags
    0.54
    MLLoader
    0.50
    Rohy
    0.48
    hove
    0.46
    getSelectedItem
    0.46
     torsion
    0.45
    esez
    0.45
    Activations Density 0.628%

    No Known Activations