© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8107
    Prev
    Next
    INDEX
    Explanations

    references to coffee, tea, and cafes

    oai_token-act-pair · gemini-2.0-flash

    coffee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     coffee
    -2.31
    Coffee
    -2.16
     Coffee
    -2.14
    coffee
    -2.05
     COFFEE
    -1.91
     coffe
    -1.66
     coffees
    -1.65
     Kaffee
    -1.55
     Coffe
    -1.48
     koffie
    -1.41
    POSITIVE LOGITS
     Gates
    0.51
     NDEBUG
    0.49
    APIView
    0.47
    WarningLevel
    0.47
     carcass
    0.47
    лимпий
    0.45
     Cæsar
    0.44
     carri
    0.43
    osoma
    0.43
    tonsoft
    0.43
    Activations Density 0.198%

    No Known Activations