© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2887
    Prev
    Next
    INDEX
    Explanations

    words related to cars and driving

    oai_token-act-pair · gemini-2.0-flash

    driving

    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
    Negative Logits
     Seeder
    -0.60
    XmlAccessType
    -0.60
    GEBURTSDATUM
    -0.55
    énage
    -0.55
    kháu
    -0.54
    вча
    -0.53
     незавершена
    -0.52
    Rujuakan
    -0.51
     arqu
    -0.51
    NameInMap
    -0.51
    POSITIVE LOGITS
     driving
    2.81
     drive
    2.81
    driving
    2.56
     drives
    2.56
     drove
    2.53
    Driving
    2.52
    drive
    2.52
     Driving
    2.48
     Drive
    2.44
    Drive
    2.39
    Activations Density 2.210%

    No Known Activations