© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13969
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and text related to sports scores and statistics

    oai_token-act-pair · gemini-2.0-flash

    languages/countries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    awaiter
    -0.70
     Infórmanos
    -0.69
    XmlAccessType
    -0.60
     ویکی‌پدیا
    -0.60
    Portály
    -0.60
    forRoot
    -0.59
     InputDecoration
    -0.57
    Попис
    -0.57
    InjectAttribute
    -0.56
     المعيارى
    -0.56
    POSITIVE LOGITS
     men
    0.58
     africains
    0.56
     Spanyol
    0.56
    曖昧さ回避
    0.56
     américa
    0.52
     defaultstate
    0.52
     Brasile
    0.50
     européennes
    0.50
     CreateTagHelper
    0.48
     pétrole
    0.48
    Activations Density 11.701%

    No Known Activations