© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10308
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions, often enclosed in dollar signs or related to differential equations

    oai_token-act-pair · gemini-2.0-flash

    Math symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    A
    -1.02
    P
    -0.95
    E
    -0.93
    H
    -0.92
    N
    -0.92
    T
    -0.91
    B
    -0.91
    X
    -0.90
    M
    -0.90
    D
    -0.90
    POSITIVE LOGITS
     S
    0.79
     L
    0.77
     C
    0.77
     Q
    0.75
     J
    0.75
     R
    0.74
     E
    0.74
    ')):
    0.73
     G
    0.73
     N
    0.72
    Activations Density 5.227%

    No Known Activations