© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4694
    Prev
    Next
    INDEX
    Explanations

    code snippets with acronyms including the letters "U" and/or "T"

    oai_token-act-pair · gemini-2.0-flash

    U

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     U
    -2.05
     US
    -1.62
    U
    -1.48
    US
    -1.18
     United
    -1.16
     USA
    -1.09
     American
    -0.95
     UK
    -0.94
    United
    -0.92
    在美国
    -0.87
    POSITIVE LOGITS
    u
    0.81
    us
    0.73
     duquel
    0.61
    uid
    0.60
     lu
    0.56
    uu
    0.56
    upu
    0.56
    tu
    0.55
    up
    0.55
     épais
    0.54
    Activations Density 0.963%

    No Known Activations