© 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. 10801
    Prev
    Next
    INDEX
    Explanations

    words that have a clear political or financial context

    oai_token-act-pair · gemini-2.0-flash

    Parenthesis and brackets

    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
     Theſe
    -0.96
     Efq
    -0.91
     itſelf
    -0.89
     ―――――
    -0.89
     Jefus
    -0.87
     ſeveral
    -0.87
    )");
    -0.86
    /−
    -0.84
     Monfieur
    -0.83
    '));
    -0.81
    POSITIVE LOGITS
     (
    2.53
     [
    1.90
     ([
    1.59
    (
    1.48
    （
    1.41
    ([
    1.34
    [
    1.31
     [(
    1.18
     ((
    1.16
     ({
    1.11
    Activations Density 3.972%

    No Known Activations