© 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. 7351
    Prev
    Next
    INDEX
    Explanations

    mentions of places, especially locations named after people, and other possible surnames

    oai_token-act-pair · gemini-2.0-flash

    Alabama

    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
    WebServlet
    -0.56
     useAppContext
    -0.54
    Билгалдахарш
    -0.54
     AttributeSet
    -0.50
    ู่
    -0.49
    __(/*!
    -0.49
     chó
    -0.48
    有事
    -0.48
    deal
    -0.47
     فريبيس
    -0.47
    POSITIVE LOGITS
     صوتيه
    0.67
     '\\;'
    0.57
     Rptr
    0.57
     roul
    0.55
    TintMode
    0.55
     }{@
    0.54
    RTEX
    0.53
     {?>
    0.53
    AccessorTable
    0.52
    centaje
    0.52
    Activations Density 0.513%

    No Known Activations