© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12416
    Prev
    Next
    INDEX
    Explanations

    statistical sports commentary also using some NBA team names and player names

    oai_token-act-pair · gemini-2.0-flash

    sports statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    MemoryWarning
    -0.81
    AndEndTag
    -0.69
     &___
    -0.63
    UnitTesting
    -0.55
    astify
    -0.55
     كومونز
    -0.55
    ViewImports
    -0.55
    offsetof
    -0.54
    endsection
    -0.54
    المناصب
    -0.54
    POSITIVE LOGITS
     averaging
    0.56
    verages
    0.54
     Ανακτήθηκε
    0.51
     SafeMath
    0.50
    thâu
    0.49
     汉
    0.48
     MainAxisSize
    0.48
     cụ
    0.47
    plevel
    0.47
     massimo
    0.47
    Activations Density 0.833%

    No Known Activations