© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6765
    Prev
    Next
    INDEX
    Explanations

    code, particularly C# and/or XAML code snippets, including references to objects, properties, and UI elements like buttons, text blocks, and combo boxes, and some anti-oxidant talk

    oai_token-act-pair · gemini-2.0-flash

    capitalized programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     voltage
    -0.52
    ariable
    -0.50
    volo
    -0.48
    voltage
    -0.47
    חק
    -0.46
    vori
    -0.46
    wirk
    -0.46
    rimento
    -0.45
    期刊论文
    -0.44
    kre
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.78
    قایناق‌لار
    0.73
     الحره
    0.69
     AssemblyCulture
    0.65
    extAlignment
    0.64
     Italijanski
    0.64
    IntoConstraints
    0.63
     للمعارف
    0.61
    PerformLayout
    0.60
     ویکی‌پدی
    0.58
    Activations Density 2.080%

    No Known Activations