© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10703
    Prev
    Next
    INDEX
    Explanations

    the word "Math" and graphics commands

    oai_token-act-pair · gemini-2.0-flash

    Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Math
    -2.13
    Math
    -2.11
     math
    -1.92
    math
    -1.89
     MATH
    -1.58
     mathematics
    -1.45
     maths
    -1.44
    MATH
    -1.38
     Mathematics
    -1.35
     Maths
    -1.28
    POSITIVE LOGITS
    posedge
    0.67
    Rhestr
    0.62
    Hentet
    0.60
     chi̍t
    0.57
    EDEFAULT
    0.57
     estekak
    0.57
    Tembelea
    0.56
    sweise
    0.54
     pulumi
    0.53
    SharedDtor
    0.53
    Activations Density 3.913%

    No Known Activations