© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11448
    Prev
    Next
    INDEX
    Explanations

    words related to ethnic restaurants and food dishes including traditional ingredients and preparation techniques

    oai_token-act-pair · gemini-2.0-flash

    traditional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    tvguidetime
    -0.68
    Westfalen
    -0.56
    cplusplus
    -0.56
     MainAxisSize
    -0.55
     Мексичка
    -0.54
    lapsingToolbar
    -0.54
     IBOutlet
    -0.54
     UITableView
    -0.54
    PAIGN
    -0.53
    eax
    -0.53
    POSITIVE LOGITS
    BufferException
    0.60
     medži
    0.57
     experts
    0.55
     transfieras
    0.54
    expert
    0.53
    woff
    0.52
    Author
    0.50
     expert
    0.49
    InvalidProtocol
    0.49
     Numerade
    0.48
    Activations Density 1.011%

    No Known Activations