© 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. 14796
    Prev
    Next
    INDEX
    Explanations

    words related to sports, especially scoring and competition

    oai_token-act-pair · gemini-2.0-flash

    sports scores

    np_max-act · gemini-2.0-flash

    scorer

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     '+':
    -0.52
    the
    -0.49
    That
    -0.46
     itu
    -0.46
     players
    -0.46
     hitters
    -0.45
    chkin
    -0.44
    <bos>
    -0.44
     arqu
    -0.44
     hitter
    -0.43
    POSITIVE LOGITS
    InjectAttribute
    1.00
     متعلقه
    0.98
    bootstrapcdn
    0.94
     CreateTagHelper
    0.88
    Hochspringen
    0.88
     للمعارف
    0.86
     فريبيس
    0.81
    complexContent
    0.80
     jspb
    0.79
    httphttps
    0.78
    Activations Density 0.541%

    No Known Activations