© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15870
    Prev
    Next
    INDEX
    Explanations

    descriptions of wines and liquors, especially their production and consumption

    oai_token-act-pair · gemini-2.0-flash

    Food and drink

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ArgumentParser
    -0.85
    RegressionTest
    -0.71
    MemoryWarning
    -0.71
    ]")]
    -0.64
    BeginInit
    -0.64
    sendFile
    -0.61
     beginnetje
    -0.59
    CodeAttribute
    -0.59
    Derbyniad
    -0.59
    ⋙
    -0.59
    POSITIVE LOGITS
     drinkers
    0.81
     drinks
    0.80
     Drinks
    0.79
     beverages
    0.79
     Drink
    0.78
    Drink
    0.76
     drunken
    0.76
     drink
    0.76
     liquor
    0.75
     drinker
    0.74
    Activations Density 0.822%

    No Known Activations