© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4097
    Prev
    Next
    INDEX
    Explanations

    words/phrases related to diets, food intake, deficiencies, and nutrients.

    oai_token-act-pair · gemini-2.0-flash

    food and nutrition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    RetentionPolicy
    -0.93
     Roskov
    -0.86
     useAppContext
    -0.85
     Normdatei
    -0.81
    🏻‍♀️
    -0.80
     InputDecoration
    -0.80
    Personendaten
    -0.78
     $_"
    -0.77
    ViewFeatures
    -0.77
    setVerticalGroup
    -0.77
    POSITIVE LOGITS
     kon
    0.48
    kon
    0.47
    let
    0.42
    X
    0.40
    x
    0.40
    ung
    0.39
    cur
    0.39
    bre
    0.39
    tra
    0.38
    Kon
    0.38
    Activations Density 2.803%

    No Known Activations