© 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. 2974
    Prev
    Next
    INDEX
    Explanations

    mentions of 'Hong Kong', locations in or related to Hong Kong, Universities, and numbers.

    oai_token-act-pair · gemini-2.0-flash

    locations

    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
     messing
    -0.57
     Pushing
    -0.55
     Makers
    -0.55
     patching
    -0.54
     tinkering
    -0.53
     buffering
    -0.52
     hovering
    -0.52
     Stepping
    -0.52
     tinker
    -0.52
    magical
    -0.52
    POSITIVE LOGITS
    ghalaya
    0.77
    Botswana
    0.75
     Latvia
    0.70
     Uzbekistan
    0.68
     Armenia
    0.68
    Armenia
    0.68
     Sulawesi
    0.67
     Surabaya
    0.67
    JAKARTA
    0.67
    ambique
    0.66
    Activations Density 14.096%

    No Known Activations