© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 544
    Prev
    Next
    INDEX
    Explanations

    words related to matrices and data structures

    oai_token-act-pair · gemini-2.0-flash

    matrix

    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
     matrix
    -1.80
     Matrix
    -1.61
    matrix
    -1.45
    Matrix
    -1.41
     MATRIX
    -1.38
     matrices
    -1.36
     Matrices
    -1.19
    矩阵
    -1.15
     matrice
    -1.14
     matriz
    -1.09
    POSITIVE LOGITS
    vább
    0.56
    ệu
    0.53
    Referencies
    0.51
    rature
    0.48
    Referanser
    0.46
    warzys
    0.44
     gửi
    0.42
     Candid
    0.42
    parsedMessage
    0.42
     XCTest
    0.41
    Activations Density 9.357%

    No Known Activations