© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4522
    Prev
    Next
    INDEX
    Explanations

    mentions of pizza toppings and descriptions

    oai_token-act-pair · gemini-2.0-flash

    words related to pizza

    np_token-act-pair-logits · gpt-4o-mini

    pizza/restaurants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    发表于
    -0.43
     ış
    -0.42
    级
    -0.41
     degree
    -0.40
    gares
    -0.39
    فحة
    -0.39
    typeorm
    -0.38
     مرک
    -0.38
    setViewportView
    -0.38
     trest
    -0.37
    POSITIVE LOGITS
     ostavi
    0.80
    rungsseite
    0.70
    RectangleBorder
    0.69
    ✨:
    0.68
     مرئيه
    0.68
    ValueGeneration
    0.65
    RefNanny
    0.65
     Giulia
    0.63
     Wicidata
    0.63
    InjectAttribute
    0.63
    Activations Density 1.248%

    No Known Activations