© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12470
    Prev
    Next
    INDEX
    Explanations

    references to food, cooking, and meals, especially healthy ones.

    oai_token-act-pair · gemini-2.0-flash

    meals and cooking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     food
    -1.02
    food
    -0.91
     Food
    -0.88
    Food
    -0.88
     FOOD
    -0.81
    FOOD
    -0.79
    tagHelperRunner
    -0.77
     nourriture
    -0.76
    DebuggerStep
    -0.71
    最快更新
    -0.70
    POSITIVE LOGITS
     Tomé
    0.56
    ANTLR
    0.46
    uts
    0.45
    Copia
    0.44
    ριν
    0.42
     fixed
    0.41
    }^{+\
    0.40
    itel
    0.40
     corso
    0.40
    ěř
    0.40
    Activations Density 1.073%

    No Known Activations