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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15313
    Prev
    Next
    INDEX
    Explanations

    words associated with government and news organizations, especially related to official statements issued at or around specific times

    oai_token-act-pair · gemini-2.0-flash

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    usermodel
    -0.59
     
    -0.57
    CreateMap
    -0.56
    ️
    -0.56
     Snell
    -0.55
    fortawesome
    -0.54
     snippetHide
    -0.54
    . 
    -0.54
    hew
    -0.52
     resourceCulture
    -0.52
    POSITIVE LOGITS
     Waray
    0.67
     Ανακτήθηκε
    0.61
    <bos>
    0.59
    XmlEnum
    0.58
     دریافت‌شده
    0.58
    engertian
    0.58
    ējās
    0.55
     ajuns
    0.54
     photolibrary
    0.53
    TagMode
    0.53
    Activations Density 3.059%

    No Known Activations