© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13717
    Prev
    Next
    INDEX
    Explanations

    words related to diet, nutrition, and health, especially in the context of studies or populations.

    oai_token-act-pair · gemini-2.0-flash

    dietary

    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
    Not in Any Lists

    No Comments

    Negative Logits
    errHandler
    -0.63
    +#+#
    -0.62
    LayoutStyle
    -0.60
    tagez
    -0.56
    出版年
    -0.56
     aapt
    -0.55
    EndTag
    -0.55
     wikipagina
    -0.54
     purpoſe
    -0.53
    ofluor
    -0.52
    POSITIVE LOGITS
    BeginContext
    0.49
     involve
    0.46
    uris
    0.45
    Hentet
    0.45
    
    0.45
    组
    0.44
    waarde
    0.44
    yii
    0.43
    UUM
    0.43
    ings
    0.43
    Activations Density 2.479%

    No Known Activations