© 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. 12466
    Prev
    Next
    INDEX
    Explanations

    words related to compensation, approval, and governance

    oai_token-act-pair · gemini-2.0-flash

    receive

    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
     فريبيس
    -0.57
     دیکھیے
    -0.56
     conosciuto
    -0.50
     snippetHide
    -0.47
    ennale
    -0.47
     Darauf
    -0.45
    styleable
    -0.44
    <caption>
    -0.43
     conoció
    -0.43
     scoperto
    -0.43
    POSITIVE LOGITS
     lenker
    0.72
     Técnico
    0.57
    UAWEI
    0.56
     qashqai
    0.55
    ThroughAttribute
    0.54
     frågan
    0.52
    vér
    0.51
     barbati
    0.50
    AndEndTag
    0.50
     Argentino
    0.50
    Activations Density 0.605%

    No Known Activations