© 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. 14288
    Prev
    Next
    INDEX
    Explanations

    code and JSON syntax including terms like "user", "result", "images", "id", "company", "logo" and "featured".

    oai_token-act-pair · gemini-2.0-flash

    Image paths/references

    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
     image
    -0.99
    image
    -0.81
     images
    -0.78
     immagini
    -0.75
     Image
    -0.73
    IMAGE
    -0.71
     imagem
    -0.70
     imagen
    -0.69
     immagine
    -0.68
     Images
    -0.66
    POSITIVE LOGITS
     lenker
    0.55
    gemeester
    0.52
    rigo
    0.51
    enderror
    0.50
    참고
    0.50
    pdp
    0.49
    basicConfig
    0.49
     économies
    0.47
    ViewFeatures
    0.46
     aguacate
    0.46
    Activations Density 3.340%

    No Known Activations