© 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. 13557
    Prev
    Next
    INDEX
    Explanations

    latex code related to math

    oai_token-act-pair · gemini-2.0-flash

    LaTeX math code

    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
    UnusedPrivate
    -0.78
     defaultstate
    -0.77
     raiſ
    -0.65
    SpringBootTest
    -0.63
     propOrder
    -0.62
    ACHUSET
    -0.61
     itſelf
    -0.60
     délé
    -0.59
    urcht
    -0.57
     StringTokenizer
    -0.57
    POSITIVE LOGITS
     Réponses
    0.56
    fol
    0.53
    atorul
    0.47
    FormBuilder
    0.46
    اف
    0.46
    QtGui
    0.46
    mul
    0.45
    diac
    0.45
    țul
    0.44
    ū
    0.44
    Activations Density 2.179%

    No Known Activations