© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12050
    Prev
    Next
    INDEX
    Explanations

    words related to the internet, social media, technology, and news

    oai_token-act-pair · gemini-2.0-flash

    news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    antMatchers
    -0.58
    setVerticalGroup
    -0.58
    ГЛА
    -0.53
     idéia
    -0.51
    fml
    -0.50
    windowFixed
    -0.50
     zvuky
    -0.50
    ญิง
    -0.48
     Erişim
    -0.46
    chemia
    -0.45
    POSITIVE LOGITS
    StandardCharsets
    0.74
    TintMode
    0.69
    ArgumentParser
    0.66
     https
    0.65
    . 
    0.64
    https
    0.63
     HasFactory
    0.63
     🤣
    0.63
    קישורים
    0.62
     snippetHide
    0.61
    Activations Density 1.863%

    No Known Activations