© 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. 7380
    Prev
    Next
    INDEX
    Explanations

    references to international organizations and entities, particularly those related to health, conservation, war, or geography.

    oai_token-act-pair · gemini-2.0-flash

    World

    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
    Personensuche
    -0.70
     <<<<<<<<<<<<<<
    -0.69
     CHtml
    -0.65
    Билгалдахарш
    -0.64
     للاسماء
    -0.63
    oredCriteria
    -0.61
    WebServlet
    -0.60
     GetEnumerator
    -0.59
     AssemblyProduct
    -0.58
    RenderAtEndOf
    -0.58
    POSITIVE LOGITS
    names
    0.43
    Petrol
    0.43
    sides
    0.43
    picker
    0.43
     Jewelry
    0.43
    heets
    0.42
     disponibilités
    0.42
    zij
    0.42
    ukunft
    0.41
    piecze
    0.40
    Activations Density 3.780%

    No Known Activations