© 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. 7115
    Prev
    Next
    INDEX
    Explanations

    relationships to the season and environment something lives in (often with "in" before it)

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    DoubleQuotes
    -0.62
     ویکی‌پدیای
    -0.50
     botines
    -0.48
    رشف
    -0.46
    MAJOR
    -0.46
     yerine
    -0.44
     disfrutando
    -0.43
     optar
    -0.43
    mael
    -0.43
    regelen
    -0.43
    POSITIVE LOGITS
     NgModule
    0.72
    NgModule
    0.67
     sumpay
    0.62
    complexContent
    0.62
    GTCX
    0.60
    FTFY
    0.58
     periods
    0.57
    )['
    0.57
     Majefty
    0.56
     Eurasia
    0.56
    Activations Density 1.601%

    No Known Activations