© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3102
    Prev
    Next
    INDEX
    Explanations

    content related to online research and news.

    oai_token-act-pair · gemini-2.0-flash

    mentions of "online" or "Internet"

    np_token-act-pair-logits · gpt-4o-mini

    online

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     houſe
    -0.58
    DoubleQuotes
    -0.57
    LookAnd
    -0.56
     ApiException
    -0.56
    ")));
    -0.56
    úgó
    -0.55
     Мексичка
    -0.55
    '])){
    -0.54
    ագրություններ
    -0.53
    findpost
    -0.52
    POSITIVE LOGITS
     online
    2.66
     Online
    2.25
    online
    2.23
    Online
    2.20
     ONLINE
    2.03
    ONLINE
    1.85
     онлайн
    1.63
    オンライン
    1.56
     internet
    1.53
     Internet
    1.50
    Activations Density 2.745%

    No Known Activations