© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11584
    Prev
    Next
    INDEX
    Explanations

    the names of people in formal contexts like news articles, or medical contexts like doctor's names

    oai_token-act-pair · gemini-2.0-flash

    government and official matters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     propOrder
    -0.66
    WebMethod
    -0.59
    öffentlichungen
    -0.54
    elif
    -0.53
    odeficiency
    -0.52
    rachtet
    -0.52
    Xna
    -0.52
     UIColor
    -0.52
     JsonConvert
    -0.51
    makeText
    -0.50
    POSITIVE LOGITS
    mobileqq
    0.57
    guntas
    0.52
    ombic
    0.50
    webElementXpaths
    0.49
     shewn
    0.48
    
    0.48
    تفصیلات
    0.48
    gonic
    0.48
     aé
    0.46
    lüğü
    0.46
    Activations Density 0.941%

    No Known Activations