© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2322
    Prev
    Next
    INDEX
    Explanations

    text related to high school graduation

    oai_token-act-pair · gemini-2.0-flash

    terms related to classes or schooling

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

    School classes

    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
    ContentAsync
    -0.72
    StructEnd
    -0.67
    AndEndTag
    -0.65
     beginnetje
    -0.64
     '-';
    -0.60
     kasarigan
    -0.60
     disambiguazione
    -0.60
     rând
    -0.59
     trajets
    -0.59
    Искәрмәләр
    -0.59
    POSITIVE LOGITS
     class
    0.79
     classes
    0.74
    class
    0.68
     classe
    0.62
     clase
    0.60
    classes
    0.58
     класс
    0.58
     класса
    0.57
     grad
    0.57
     AP
    0.55
    Activations Density 8.334%

    No Known Activations