© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10034
    Prev
    Next
    INDEX
    Explanations

    tokens that are descriptive of food or eating at a restaurant, including positive and negative descriptions of the experience.

    oai_token-act-pair · gemini-2.0-flash

    gifts and meals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    IsContent
    -0.95
     محفوظة
    -0.66
    MarshalTo
    -0.65
    CppMethod
    -0.62
     uLocal
    -0.62
    []=$
    -0.62
    AddTagHelper
    -0.61
    ">//
    -0.61
     بيها
    -0.60
     ProtoMessage
    -0.60
    POSITIVE LOGITS
     gifts
    0.68
     gift
    0.65
     Christmas
    0.64
     lunch
    0.64
     dinner
    0.63
     supper
    0.63
     breakfast
    0.62
     snack
    0.61
     desayuno
    0.58
     christmas
    0.58
    Activations Density 1.040%

    No Known Activations