© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10264
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sports games

    oai_token-act-pair · gemini-2.0-flash

    sports outcomes

    np_token-act-pair-logits · gpt-4o-mini

    sports game results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    StoryboardSegue
    -0.93
    StructEnd
    -0.90
    webElementXpaths
    -0.90
    findpost
    -0.89
     ModelExpression
    -0.89
    OGND
    -0.88
     myſelf
    -0.88
    aarrggbb
    -0.87
    ThroughAttribute
    -0.84
    DeleteBehavior
    -0.81
    POSITIVE LOGITS
     result
    0.59
     over
    0.57
     win
    0.54
     
    0.50
     double
    0.49
     run
    0.48
     let
    0.47
     triple
    0.45
     close
    0.44
     come
    0.44
    Activations Density 0.634%

    No Known Activations