© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10280
    Prev
    Next
    INDEX
    Explanations

    mathematics notation

    oai_token-act-pair · gemini-2.0-flash

    mathematical text

    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
    Negative Logits
    entraî
    -0.46
     Bastille
    -0.46
     Portions
    -0.44
    Postup
    -0.43
     ado
    -0.43
    reportWebVitals
    -0.41
    entiment
    -0.40
    entiary
    -0.40
     Kür
    -0.40
    tone
    -0.40
    POSITIVE LOGITS
    AxisAlignment
    0.68
    GEBURTSDATUM
    0.67
     geslacht
    0.65
    setupUi
    0.60
     push
    0.59
    principalTable
    0.59
    complexContent
    0.57
    createCanvas
    0.57
    __*/
    0.57
     насељу
    0.56
    Activations Density 2.953%

    No Known Activations