© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6105
    Prev
    Next
    INDEX
    Explanations

    text related to eating and health

    oai_token-act-pair · gemini-2.0-flash

    healthy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    contentLoaded
    -0.79
    ArgsConstructor
    -0.66
    XmlRootElement
    -0.62
     nahilalakip
    -0.62
     snippetHide
    -0.60
    expandindo
    -0.60
    ANCIAL
    -0.59
    fortawesome
    -0.57
     durer
    -0.57
    XmlAccessType
    -0.57
    POSITIVE LOGITS
     healthy
    1.52
    healthy
    1.35
     healthier
    1.30
    Healthy
    1.23
     healthiest
    1.20
     Healthy
    1.19
     health
    1.18
     healthful
    1.11
     HEALTH
    1.09
    health
    1.06
    Activations Density 0.692%

    No Known Activations