© 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. 13239
    Prev
    Next
    INDEX
    Explanations

    words used in scientific publications, including medical terminology, study design, and hospital names

    oai_token-act-pair · gemini-2.0-flash

    between

    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
    rrggbb
    -0.62
     nont
    -0.54
    ArrowToggle
    -0.52
    zegor
    -0.51
    ynchronously
    -0.50
    Билгалдахарш
    -0.50
     ***!
    -0.49
     chi̍t
    -0.48
    íč
    -0.47
     disambiguazione
    -0.47
    POSITIVE LOGITS
     between
    2.78
    between
    2.48
    Between
    2.45
     Between
    2.45
     BETWEEN
    2.30
    BETWEEN
    2.05
     zwischen
    2.00
     tussen
    1.98
     mellan
    1.98
     между
    1.82
    Activations Density 2.640%

    No Known Activations