© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9345
    Prev
    Next
    INDEX
    Explanations

    words related to Indian/Malaysian food or restaurants, especially items containing chicken, and restaurant reviews.

    oai_token-act-pair · gemini-2.0-flash

    chicken

    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
    Negative Logits
     nahilalakip
    -1.00
     chicken
    -0.77
     Chicken
    -0.68
    Chicken
    -0.66
    ViewFeatures
    -0.64
    chicken
    -0.64
     CHICKEN
    -0.63
     chickens
    -0.55
    Хьажоргаш
    -0.55
    ServiceModel
    -0.54
    POSITIVE LOGITS
     ujednoznacz
    0.73
    aarrggbb
    0.57
     linkovi
    0.51
    Unnamed
    0.50
    HomeAsUp
    0.50
    Geplaatst
    0.49
    ressão
    0.49
    ArrowToggle
    0.48
    AddTagHelper
    0.48
     memo
    0.47
    Activations Density 14.296%

    No Known Activations