© 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. 12610
    Prev
    Next
    INDEX
    Explanations

    words that represent countries or people in a country

    oai_token-act-pair · gemini-2.0-flash

    Africa-related news/reports

    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
    Personendaten
    -0.74
     مشين
    -0.73
     AssemblyProduct
    -0.72
    Personensuche
    -0.72
    NameInMap
    -0.68
    MemoryWarning
    -0.64
    InstrumentedTest
    -0.64
    UnusedPrivate
    -0.61
    parsedMessage
    -0.61
    principalTable
    -0.60
    POSITIVE LOGITS
    ISTRATION
    0.50
    WebServlet
    0.49
    spesies
    0.47
     Kere
    0.46
    kela
    0.46
    +:+
    0.45
    empêcher
    0.44
     Aram
    0.44
    PACS
    0.44
     OB
    0.43
    Activations Density 14.794%

    No Known Activations