© 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. 7027
    Prev
    Next
    INDEX
    Explanations

    mentions of cities, towns, and government actions like curfews and suspensions

    oai_token-act-pair · gemini-2.0-flash

    news articles

    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
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.74
     Monfieur
    -0.72
    ImageContext
    -0.70
    Дереккөздер
    -0.68
    TagMode
    -0.67
    المكان
    -0.67
    ConstraintMaker
    -0.67
     ſmall
    -0.66
     myſelf
    -0.65
    IUrlHelper
    -0.64
    POSITIVE LOGITS
    yarnpkg
    0.51
    #
    0.51
     ever
    0.48
     appre
    0.47
     Ter
    0.47
     strictement
    0.46
     laud
    0.45
    روم
    0.43
    newswire
    0.43
     writeTo
    0.43
    Activations Density 9.160%

    No Known Activations