© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2831
    Prev
    Next
    INDEX
    Explanations

    phrases related to horse or dog racing

    oai_token-act-pair · gemini-2.0-flash

    horse racing/Kentucky

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    utnik
    -0.65
     تضيفلها
    -0.57
     numberOfRows
    -0.57
     HasFactory
    -0.52
     Gorman
    -0.51
    derry
    -0.51
    PyExc
    -0.51
    GOTREF
    -0.51
    統領
    -0.50
     Straus
    -0.50
    POSITIVE LOGITS
    XtraEditors
    0.60
    DoubleQuotes
    0.56
    typeorm
    0.54
    bly
    0.50
    XtraGrid
    0.50
     médaille
    0.49
    ContentAsync
    0.49
    cjonal
    0.49
    tagext
    0.48
     veneta
    0.47
    Activations Density 0.281%

    No Known Activations