© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13409
    Prev
    Next
    INDEX
    Explanations

    references to the Soviet Union and the Eastern European countries associated with it

    oai_token-act-pair · gemini-2.0-flash

    Soviet Union, former 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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    yship
    -0.55
    #
    -0.52
     transfieras
    -0.51
    XmlAttribute
    -0.50
    IntoConstraints
    -0.49
     Caucus
    -0.49
    Disposition
    -0.48
     caucus
    -0.48
    Chem
    -0.48
    يميديا
    -0.48
    POSITIVE LOGITS
    ⓧ
    0.84
     <=",
    0.68
    MemoryWarning
    0.65
    ArrowToggle
    0.60
    pulumi
    0.59
    sizeCache
    0.58
    Խ
    0.56
    encodeWith
    0.54
     Auflage
    0.53
    queryInterface
    0.53
    Activations Density 1.441%

    No Known Activations