© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10969
    Prev
    Next
    INDEX
    Explanations

    the word "ball" and related words, particularly in contexts of games, sports

    oai_token-act-pair · gemini-2.0-flash

    ball

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     some
    -0.80
     now
    -0.64
     even
    -0.62
     not
    -0.62
     new
    -0.59
     fact
    -0.59
     last
    -0.59
     then
    -0.57
     the
    -0.57
     most
    -0.56
    POSITIVE LOGITS
     nakalista
    0.90
    Tikang
    0.87
     gills
    0.84
     poetical
    0.82
     {*}
    0.80
     ©️
    0.80
    تقاوى
    0.79
     للاسماء
    0.79
     énergé
    0.79
     Мексичка
    0.79
    Activations Density 2.253%

    No Known Activations