© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10177
    Prev
    Next
    INDEX
    Explanations

    a variety of numbers, codes, and identifiers within various data formats, including scientific and web-related contexts.

    oai_token-act-pair · gemini-2.0-flash

    processing data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ily
    -0.48
    ც
    -0.46
     tu
    -0.42
    xx
    -0.42
    ses
    -0.42
     ait
    -0.42
     lo
    -0.41
     ay
    -0.41
     gn
    -0.41
     tue
    -0.41
    POSITIVE LOGITS
    MigrationBuilder
    1.02
     resourceCulture
    0.85
     ویکی‌پدیا
    0.85
    WebVitals
    0.79
    DockStyle
    0.76
    ConstraintMaker
    0.76
     defaultstate
    0.75
    ValueStyle
    0.72
    EndGlobalSection
    0.71
     CreateTagHelper
    0.70
    Activations Density 18.143%

    No Known Activations