© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3950
    Prev
    Next
    INDEX
    Explanations

    text referring to military and political entities, especially those related to the US military and NATO.

    oai_token-act-pair · gemini-2.0-flash

    Military and geopolitical contexts

    np_max-act-logits · 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
     ujednoznacz
    -0.74
    Controllo
    -0.71
    elemField
    -0.66
    queryInterface
    -0.65
    ooker
    -0.65
    TypedDataSet
    -0.61
    الحياه
    -0.61
     насељу
    -0.61
     initComponents
    -0.60
    Билгалдахарш
    -0.60
    POSITIVE LOGITS
    IonicModule
    0.52
     iprot
    0.52
     sindaco
    0.50
    regalo
    0.45
     Stringer
    0.43
    TestBase
    0.42
     torno
    0.42
    ربعة
    0.40
    AutoresizingMask
    0.40
     garanzia
    0.40
    Activations Density 1.170%

    No Known Activations