© 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. 9764
    Prev
    Next
    INDEX
    Explanations

    words or phrases relating to politics, governments, war, violence, and conflict

    oai_token-act-pair · gemini-2.0-flash

    political unrest

    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
    idemia
    -0.70
    IBOutlet
    -0.68
    richTextPanel
    -0.66
    adaptiveStyles
    -0.65
    ArrowToggle
    -0.63
    دانشنامهٔ
    -0.63
    сылкі
    -0.62
     OnInit
    -0.59
     AssemblyTitle
    -0.57
     تانيه
    -0.57
    POSITIVE LOGITS
    addGap
    0.63
    könig
    0.56
     Projected
    0.52
     jugement
    0.50
     comunista
    0.49
     magique
    0.48
    Stalin
    0.48
     Stalin
    0.47
     projected
    0.47
    !("
    0.47
    Activations Density 6.274%

    No Known Activations