© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9922
    Prev
    Next
    INDEX
    Explanations

    names of ingredients and dishes associated with Italian and Mexican foods

    oai_token-act-pair · gemini-2.0-flash

    cooking and recipes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SearchParams
    -0.56
    enumi
    -0.51
    ônicos
    -0.50
    녕
    -0.50
    enumii
    -0.50
     içi
    -0.48
    Races
    -0.48
     प्रोडक्ट
    -0.48
    apimachinery
    -0.48
    JvmStatic
    -0.48
    POSITIVE LOGITS
     chiff
    0.58
    :+:
    0.55
     Orient
    0.52
    TagMode
    0.51
    EndContext
    0.50
     Chim
    0.50
    ExtendWith
    0.49
     OFDb
    0.49
     تضيفلها
    0.49
    protoimpl
    0.48
    Activations Density 0.813%

    No Known Activations