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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11393
    Prev
    Next
    INDEX
    Explanations

    descriptions of food, especially focusing on flavour and preparation

    oai_token-act-pair · gemini-2.0-flash

    words related to delicious food

    np_token-act-pair-logits · gpt-4o-mini

    food reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Stande
    -0.57
     Вікі
    -0.55
    tawa
    -0.53
    testens
    -0.50
     NSCoder
    -0.50
    åt
    -0.47
    Portály
    -0.47
    CascadeType
    -0.46
    asen
    -0.46
    benzo
    -0.45
    POSITIVE LOGITS
     délicieux
    0.58
    γη
    0.56
     yum
    0.55
    Vidite
    0.55
     del
    0.54
     rafraî
    0.52
    omitempty
    0.52
    EndContext
    0.52
     récon
    0.52
     delicious
    0.51
    Activations Density 0.731%

    No Known Activations