© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15315
    Prev
    Next
    INDEX
    Explanations

    technical and scientific language with numbers and percentages, especially in the context of medical studies and comparisons

    oai_token-act-pair · gemini-2.0-flash

    compared

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     وتسجيلات
    -0.75
    Hochspringen
    -0.73
    expandindo
    -0.73
    MethodManager
    -0.70
    LookAnd
    -0.70
    addCriterion
    -0.70
    PYX
    -0.68
    ValueStyle
    -0.68
     EconPapers
    -0.67
     Signalez
    -0.67
    POSITIVE LOGITS
    eg
    0.63
    ={({
    0.48
     &
    0.47
    емо
    0.46
    ache
    0.46
     perche
    0.46
    örung
    0.45
     Whereas
    0.45
    mo
    0.45
     yr
    0.44
    Activations Density 7.454%

    No Known Activations