© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4844
    Prev
    Next
    INDEX
    Explanations

    mentions of food, specifically rice

    oai_token-act-pair · gemini-2.0-flash

    rice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Téléchargez
    -0.52
    ungszeit
    -0.49
     Council
    -0.47
     Pension
    -0.47
     council
    -0.47
     Quinn
    -0.46
     miền
    -0.46
     COUNCIL
    -0.45
    ❋
    -0.45
    pix
    -0.45
    POSITIVE LOGITS
     rice
    0.63
    脚注の使い方
    0.62
    SpringBootTest
    0.58
    abestanden
    0.57
    🍚
    0.57
    ,:);
    0.56
    AsUp
    0.56
     Rice
    0.56
     дописавши
    0.55
    Rice
    0.55
    Activations Density 1.094%

    No Known Activations