© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13579
    Prev
    Next
    INDEX
    Explanations

    geographic locations and geopolitical terms, particularly those in northern Europe

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     betweenstory
    -0.99
    Tembelea
    -0.79
     <=",
    -0.76
    مصادر
    -0.74
    dafx
    -0.69
    quins
    -0.69
    SharedDtor
    -0.68
     Himo
    -0.65
    chyma
    -0.63
     ویکی‌پدی
    -0.62
    POSITIVE LOGITS
    MLLoader
    0.57
    MockMvc
    0.46
    க்கு
    0.40
     di
    0.40
    ByteBuf
    0.39
     demand
    0.38
    Itoa
    0.36
    abang
    0.35
    ่านั้น
    0.35
    
    0.34
    Activations Density 0.140%

    No Known Activations