© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5491
    Prev
    Next
    INDEX
    Explanations

    the word "that"

    oai_token-act-pair · gemini-2.0-flash

    words related to relationships and togetherness

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

    that

    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
    enumii
    -0.72
    RepeatedField
    -0.63
    Viited
    -0.63
    parsedMessage
    -0.61
     ་་
    -0.60
    XmlAttribute
    -0.58
    HttpEntity
    -0.58
     Jue
    -0.57
    <?
    -0.57
    iseries
    -0.57
    POSITIVE LOGITS
     we
    0.79
     you
    0.74
     they
    0.73
     has
    0.73
     is
    0.68
     the
    0.68
     requires
    0.67
     includes
    0.67
     these
    0.66
     contains
    0.65
    Activations Density 4.381%

    No Known Activations