© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13260
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to web navigation, online forms, economics, and research panel participation.

    oai_token-act-pair · gemini-2.0-flash

    plural items

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Clik
    -0.65
     inconvénients
    -0.64
     débats
    -0.60
     rigue
    -0.60
     preuves
    -0.59
     centaines
    -0.59
     dizaines
    -0.59
     lèvres
    -0.57
     schermata
    -0.57
     générations
    -0.56
    POSITIVE LOGITS
     actions
    0.74
     transactions
    0.72
     products
    0.71
     songs
    0.70
     items
    0.70
     sentences
    0.65
     dishes
    0.64
     jobs
    0.63
     sessions
    0.63
     articles
    0.63
    Activations Density 4.228%

    No Known Activations