© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10118
    Prev
    Next
    INDEX
    Explanations

    long strings of digits, often negative, in a variety of contexts including percentages, mathematical series, and medical findings.

    oai_token-act-pair · gemini-2.0-flash

    ordinal numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    endphp
    -0.71
    AndroidJUnit
    -0.68
    !*\
    -0.66
    complexContent
    -0.64
    makeText
    -0.62
    RenderAtEndOf
    -0.60
    bootstrapcdn
    -0.59
    UAGES
    -0.59
    onViewCreated
    -0.58
    ///</
    -0.57
    POSITIVE LOGITS
     eighth
    0.65
    8
    0.63
     ninth
    0.62
    9
    0.60
    第八
    0.59
     nine
    0.56
     seventh
    0.56
    7
    0.54
    第九
    0.54
     eight
    0.53
    Activations Density 1.347%

    No Known Activations