© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15710
    Prev
    Next
    INDEX
    Explanations

    references to Honduras and its politics in the context of US foreign policy, economics and the CIA.

    oai_token-act-pair · gemini-2.0-flash

    countries and rulers

    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
     Mal
    -1.07
     Gamb
    -1.04
     Ang
    -0.96
     Nic
    -0.94
     Tog
    -0.90
     Cong
    -0.87
    Mal
    -0.85
     Cam
    -0.85
     Liber
    -0.84
     Moz
    -0.84
    POSITIVE LOGITS
     Chernobyl
    0.60
     Talmud
    0.59
    非洲
    0.59
     الرياضيه
    0.58
     tropicales
    0.57
     Confucian
    0.57
     Vedas
    0.56
     coreano
    0.54
     africano
    0.54
     ſtate
    0.54
    Activations Density 1.491%

    No Known Activations