© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7300
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to the start of a race, particularly horse or dog racing, and potentially also the location of races

    oai_token-act-pair · gemini-2.0-flash

    Racing and sports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Efq
    -1.00
     itſelf
    -0.97
     myſelf
    -0.96
     TextAppearance
    -0.90
     Shakspeare
    -0.88
     Monfieur
    -0.87
     Theſe
    -0.85
    IsContent
    -0.83
    contentLoaded
    -0.82
     ―――――
    -0.82
    POSITIVE LOGITS
    ност
    0.39
    看好
    0.37
     Teknik
    0.36
     Par
    0.35
    tok
    0.35
     tud
    0.34
     Preservation
    0.34
    ور
    0.34
     head
    0.34
     dom
    0.33
    Activations Density 0.688%

    No Known Activations