© 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. 13370
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions including symbols, equations, or numerical sequences

    oai_token-act-pair · gemini-2.0-flash

    Math series and convergence

    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
    SharedDtor
    -0.68
    esModule
    -0.60
    ()])
    -0.56
    ReusableCell
    -0.51
     GNA
    -0.51
    ')){
    -0.51
    enterOuterAlt
    -0.50
    〕
    -0.49
    opsida
    -0.49
    ')));
    -0.48
    POSITIVE LOGITS
    ابط
    0.54
     &_
    0.52
    SourceChecksum
    0.49
    masing
    0.49
    ptid
    0.48
    RepeatedField
    0.48
     serien
    0.47
    arası
    0.46
    áže
    0.46
    Personensuche
    0.46
    Activations Density 0.930%

    No Known Activations