© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9851
    Prev
    Next
    INDEX
    Explanations

    food items, especially fruits and vegetables

    oai_token-act-pair · gemini-2.0-flash

    food ingredients

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     télévis
    -0.55
    zeige
    -0.50
    impianto
    -0.48
    בים
    -0.45
     bajo
    -0.45
    хни
    -0.44
     numérique
    -0.44
     renovables
    -0.42
     deportivas
    -0.42
     gạch
    -0.42
    POSITIVE LOGITS
    TagMode
    0.73
     nahilalakip
    0.66
     HttpHeaders
    0.65
    RenderAtEndOf
    0.64
    UnsafeEnabled
    0.63
    principalColumn
    0.61
     للمعارف
    0.60
    setViewportView
    0.60
    BeginContext
    0.60
    ChildScrollView
    0.59
    Activations Density 0.461%

    No Known Activations