© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15589
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, especially in addresses

    oai_token-act-pair · gemini-2.0-flash

    Texas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Zeneca
    -0.56
    ########.
    -0.52
     Wiktionnaire
    -0.49
    úgó
    -0.49
     InputDecoration
    -0.48
     Bourne
    -0.47
    MCA
    -0.47
     ويكيپيديا
    -0.46
    usermodel
    -0.45
    dirond
    -0.45
    POSITIVE LOGITS
     Texas
    1.20
     TEXAS
    1.13
    Texas
    1.08
     TX
    1.01
     Tx
    0.99
     Austin
    0.97
    texas
    0.95
     AUSTIN
    0.94
     texas
    0.94
     Texan
    0.93
    Activations Density 1.015%

    No Known Activations