© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9838
    Prev
    Next
    INDEX
    Explanations

    references to Nazi Germany, the Soviet Union or other communist countries, especially around the time of WWII.

    oai_token-act-pair · gemini-2.0-flash

    Nazi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     متعلقه
    -0.64
    BeginContext
    -0.52
    InMillis
    -0.50
    roek
    -0.49
    oum
    -0.49
    IVEREF
    -0.48
    Morfologia
    -0.48
    ExecuteReader
    -0.48
     prodigal
    -0.47
    TouchEvent
    -0.47
    POSITIVE LOGITS
     Nazi
    0.81
     Gesta
    0.72
    Hitler
    0.70
     Hitler
    0.69
     Axis
    0.68
    TestingModule
    0.66
     Nazis
    0.65
     NSD
    0.64
     concentration
    0.63
     Germany
    0.62
    Activations Density 1.080%

    No Known Activations