© 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. 13353
    Prev
    Next
    INDEX
    Explanations

    words associated with diving and gymnastics related to the Olympics

    oai_token-act-pair · gemini-2.0-flash

    diving

    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
    issau
    -0.54
     مواليد
    -0.51
    فاض
    -0.50
    otheby
    -0.49
    luxury
    -0.49
    shutil
    -0.49
    стви
    -0.48
    InjectAttribute
    -0.48
     exquisite
    -0.48
    quisite
    -0.48
    POSITIVE LOGITS
     Reſ
    0.69
     skates
    0.66
     skaters
    0.64
     gymnastics
    0.60
     Vikipedi
    0.60
     crin
    0.60
     Conſ
    0.60
     juſ
    0.59
     Gymnastics
    0.59
     leſs
    0.59
    Activations Density 2.110%

    No Known Activations