© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15953
    Prev
    Next
    INDEX
    Explanations

    text from interviews, particularly questions and answers marked by colons

    oai_token-act-pair · gemini-2.0-flash

    meaning "sure"

    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
     kaarangay
    -0.65
     AssemblyProduct
    -0.62
    LookAnd
    -0.60
     censiti
    -0.52
    oneofs
    -0.52
     unknownFields
    -0.52
     चीज़ों
    -0.52
     defaultstate
    -0.51
     ModelRenderer
    -0.49
    exitRule
    -0.49
    POSITIVE LOGITS
     sure
    0.68
     Certainly
    0.60
     seguro
    0.58
     تانيه
    0.56
     sûr
    0.54
     sikkert
    0.54
     jist
    0.54
     naturligt
    0.53
     certainly
    0.52
    sure
    0.52
    Activations Density 0.668%

    No Known Activations