© 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. 9891
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to national security preparedness

    oai_token-act-pair · gemini-2.0-flash

    threats

    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
     threaten
    -2.30
     threat
    -2.28
    Threat
    -2.27
    threat
    -2.25
     threatening
    -2.23
     threatened
    -2.23
     threats
    -2.19
     Threat
    -2.16
     threatens
    -2.08
     Threats
    -2.06
    POSITIVE LOGITS
     BoxDecoration
    0.77
    клопе
    0.65
     IndexPath
    0.57
    uxxxx
    0.56
     StatefulWidget
    0.52
     ANGELES
    0.50
     implicitly
    0.49
    ték
    0.49
    Especificações
    0.48
     Italijanski
    0.48
    Activations Density 1.373%

    No Known Activations