© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 594
    Prev
    Next
    INDEX
    Explanations

    words related to drinking, eating, and folklore characters

    oai_token-act-pair · gemini-2.0-flash

    drink

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     drink
    -1.91
     Drink
    -1.69
    drink
    -1.66
     drinking
    -1.66
     drinks
    -1.63
    Drink
    -1.55
     beer
    -1.51
     DRINK
    -1.51
     wine
    -1.45
    drinks
    -1.43
    POSITIVE LOGITS
    MessageTagHelper
    0.63
    vician
    0.60
    tagext
    0.59
     صوتيه
    0.58
    новниш
    0.55
     propOrder
    0.55
    Derbyniad
    0.51
    ollectionView
    0.51
     resourceCulture
    0.50
    Montag
    0.49
    Activations Density 10.455%

    No Known Activations