© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9280
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation, especially related to graph theory and analysis

    oai_token-act-pair · gemini-2.0-flash

    rel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    󠁮
    -0.70
    portál
    -0.68
     незавершена
    -0.64
    VIAF
    -0.59
    édrale
    -0.59
     transposition
    -0.56
    RectangleBorder
    -0.55
     saites
    -0.55
    brtc
    -0.55
    openzeppelin
    -0.55
    POSITIVE LOGITS
    RunAsync
    0.58
    RenderAtEndOf
    0.51
    enterOuterAlt
    0.50
    ttle
    0.43
     puissiez
    0.42
     propOrder
    0.41
    Begriffsklä
    0.41
    XmlType
    0.40
     BoxFit
    0.39
    Edm
    0.39
    Activations Density 8.769%

    No Known Activations