© 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. 10750
    Prev
    Next
    INDEX
    Explanations

    instances of someone addressing someone else

    oai_token-act-pair · gemini-2.0-flash

    say "know"

    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
    ינוך
    -0.66
     olympiques
    -0.65
    routeProvider
    -0.63
     définiti
    -0.61
    ItemBackground
    -0.60
    IntoConstraints
    -0.59
     mijne
    -0.58
    клопе
    -0.58
    CloseOperation
    -0.57
    CppMethod
    -0.56
    POSITIVE LOGITS
     steal
    0.64
     execute
    0.62
     sit
    0.60
     spend
    0.59
     expose
    0.58
     eat
    0.57
     kill
    0.57
     take
    0.57
     join
    0.57
     sustain
    0.56
    Activations Density 1.395%

    No Known Activations