© 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. 1526
    Prev
    Next
    INDEX
    Explanations

    sentences about sitting

    oai_token-act-pair · gemini-2.0-flash

    sit

    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
     sit
    -2.39
     sitting
    -2.19
     sits
    -2.03
     Sitting
    -2.02
     sat
    -2.02
    Sitting
    -1.95
    Sit
    -1.80
    sitting
    -1.80
    sit
    -1.77
     Sit
    -1.66
    POSITIVE LOGITS
    
    0.73
     FontWeight
    0.71
    iastes
    0.70
    moschino
    0.59
     Exacts
    0.57
    multicolumn
    0.57
    discharge
    0.56
    رشف
    0.56
    chanical
    0.56
     pinulongan
    0.56
    Activations Density 9.276%

    No Known Activations