© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6741
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and numerical data with associated symbols, sometimes including medical context.

    oai_token-act-pair · gemini-2.0-flash

    code/database/scientific

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     CU
    -1.23
     RU
    -1.20
    CU
    -1.20
     BU
    -1.18
     MU
    -1.17
    PU
    -1.17
     PU
    -1.17
     DU
    -1.16
    MU
    -1.13
    DU
    -1.12
    POSITIVE LOGITS
     EconPapers
    0.71
     AssemblyCulture
    0.71
     typelib
    0.66
    AddTagHelper
    0.62
    TargetException
    0.57
    utilisons
    0.56
    angliski
    0.54
    Koordinaten
    0.53
     CreateTagHelper
    0.52
    Rhestr
    0.50
    Activations Density 0.391%

    No Known Activations