© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4682
    Prev
    Next
    INDEX
    Explanations

    terms related to American football and baseball, especially injuries and specific players

    oai_token-act-pair · gemini-2.0-flash

    warm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ConverterFactory
    -0.57
     AssemblyCulture
    -0.57
    Atsauces
    -0.54
    IntoConstraints
    -0.51
    AddHtmlAttribute
    -0.51
    InlineData
    -0.50
    AndEndTag
    -0.48
    SafeMath
    -0.47
    erà
    -0.46
     Guille
    -0.46
    POSITIVE LOGITS
     warm
    2.36
     Warm
    2.11
    Warm
    2.08
    warm
    2.03
     WARM
    1.97
     warmed
    1.91
    WARM
    1.86
     warms
    1.84
     warming
    1.72
     warmer
    1.67
    Activations Density 1.642%

    No Known Activations