© 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. 13491
    Prev
    Next
    INDEX
    Explanations

    words associated with evolution and the passage of time, particularly in the context of genetic change and scientific studies.

    oai_token-act-pair · gemini-2.0-flash

    time

    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
     שוליים
    -0.71
    KommentareTeilen
    -0.68
     ویکی‌پدیا
    -0.68
    rinfo
    -0.63
     Audiodateien
    -0.62
     surla
    -0.59
    éndole
    -0.59
    DockStyle
    -0.59
     numberOfRows
    -0.59
    ArgumentParser
    -0.58
    POSITIVE LOGITS
    seteq
    0.44
     habang
    0.39
    readyState
    0.39
    Geplaatst
    0.38
    updater
    0.38
    ölkerung
    0.37
     esternos
    0.37
     ressort
    0.37
    domada
    0.36
     colesterol
    0.36
    Activations Density 9.342%

    No Known Activations