© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11878
    Prev
    Next
    INDEX
    Explanations

    language related to sports, specifically American football.

    oai_token-act-pair · gemini-2.0-flash

    football positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ″]
    -0.40
    feld
    -0.39
    GenerationType
    -0.38
     altas
    -0.37
    wiek
    -0.36
    config
    -0.35
     GenerationType
    -0.35
     /\.(
    -0.34
     alti
    -0.34
    tlement
    -0.34
    POSITIVE LOGITS
     wide
    1.28
     running
    1.17
     defensive
    1.15
     receiver
    1.13
     tight
    1.13
     safety
    1.11
     WR
    1.10
     Wide
    1.10
    safety
    1.09
     receivers
    1.08
    Activations Density 3.037%

    No Known Activations