© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4692
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with sports and time

    oai_token-act-pair · gemini-2.0-flash

    sports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    isDebugEnabled
    -0.51
    final
    -0.48
     final
    -0.46
     तै
    -0.43
     culminating
    -0.43
     before
    -0.43
    追い
    -0.42
    yargs
    -0.42
     finishing
    -0.41
    락
    -0.40
    POSITIVE LOGITS
    Datuak
    0.88
     &___
    0.83
    oa̍t
    0.81
    Personendaten
    0.81
    AccessorTable
    0.77
    mergeFrom
    0.74
     незавершена
    0.73
    ThroughAttribute
    0.72
     насељу
    0.71
     وتسجيلات
    0.70
    Activations Density 0.982%

    No Known Activations