© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13602
    Prev
    Next
    INDEX
    Explanations

    technical language from scientific or medical papers, often connected to mathematical formulas.

    oai_token-act-pair · gemini-2.0-flash

    say "sub" words

    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
    rungsseite
    -0.90
     Efq
    -0.81
     समीक्षाओं
    -0.80
     للمعارف
    -0.79
     houſe
    -0.78
     BIBSYS
    -0.76
     bershka
    -0.76
     iprot
    -0.73
     perſon
    -0.69
    addCriterion
    -0.68
    POSITIVE LOGITS
     sub
    1.98
    sub
    1.60
     Sub
    1.54
    Sub
    1.43
     SUB
    1.27
    SUB
    1.20
    サブ
    1.16
     getSub
    1.12
     subs
    1.08
    getSub
    1.02
    Activations Density 5.660%

    No Known Activations