© 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. 9462
    Prev
    Next
    INDEX
    Explanations

    terms related to international politics and terrorism

    oai_token-act-pair · gemini-2.0-flash

    foreign

    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
    :✨
    -0.93
    hoeddwyd
    -0.87
    IsMutable
    -0.82
    migrationBuilder
    -0.77
     ujednoznacz
    -0.70
    GEBURTSDATUM
    -0.69
    ArgsConstructor
    -0.69
    fjspx
    -0.67
    GIVEREF
    -0.67
    ScopeManager
    -0.66
    POSITIVE LOGITS
     Investors
    0.50
     للمعارف
    0.46
    ListModule
    0.46
     hunters
    0.46
    ventude
    0.45
    roleum
    0.44
     commonwealth
    0.44
     investors
    0.43
     Cliente
    0.43
    FontOfSize
    0.43
    Activations Density 1.348%

    No Known Activations