© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 567
    Prev
    Next
    INDEX
    Explanations

    job titles including the word "President" or "Vice President"

    oai_token-act-pair · gemini-2.0-flash

    president

    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
     gearbox
    -0.54
     Gear
    -0.42
     nhé
    -0.42
    学生
    -0.41
     clutch
    -0.41
     students
    -0.40
    Clutch
    -0.39
    ↵↵
    -0.39
    ://
    -0.39
     transmissions
    -0.39
    POSITIVE LOGITS
     ujednoznacz
    0.90
    AnchorStyles
    0.82
     ویکی‌پدیا
    0.80
    tagHelperRunner
    0.79
    сылкі
    0.74
     habet
    0.73
    reportWebVitals
    0.71
     saites
    0.70
     awakeFromNib
    0.70
    出版年
    0.70
    Activations Density 0.331%

    No Known Activations