© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2709
    Prev
    Next
    INDEX
    Explanations

    words related to sports and martial arts

    oai_token-act-pair · gemini-2.0-flash

    martial arts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ]")]
    -0.50
    weder
    -0.49
    vores
    -0.49
     Telescope
    -0.48
    hlte
    -0.48
    timewa
    -0.47
    knecht
    -0.46
    ]--;
    -0.46
    ípio
    -0.46
    ophage
    -0.46
    POSITIVE LOGITS
    <bos>
    0.84
     karate
    0.68
    ekwondo
    0.67
     Vikipedi
    0.66
    Scénario
    0.65
    Personendaten
    0.62
     mourut
    0.61
     étoient
    0.60
     destinées
    0.60
    Personensuche
    0.60
    Activations Density 0.544%

    No Known Activations