© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13507
    Prev
    Next
    INDEX
    Explanations

    words related to canoeing, beekeeping, computing, power, and Wicca.

    oai_token-act-pair · gemini-2.0-flash

    activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ligkeit
    -0.55
    micamente
    -0.54
    createFrom
    -0.51
    หว่าง
    -0.48
    ριν
    -0.47
     cu
    -0.47
     ulang
    -0.46
     Seelen
    -0.46
    وردار
    -0.45
    çois
    -0.45
    POSITIVE LOGITS
    Portail
    0.70
    windowFixed
    0.66
     ویکی‌پدی
    0.64
     Cæsar
    0.61
     ostavi
    0.57
     resultCode
    0.56
    '])){
    0.54
    fromnode
    0.54
    Portály
    0.53
     yaris
    0.53
    Activations Density 2.551%

    No Known Activations