© 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. 9833
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "what" followed by a form of the verb "to be" (is, was, are, etc.)

    oai_token-act-pair · gemini-2.0-flash

    usage of "what" in different contexts

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

    what

    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
    ScopeManager
    -0.85
     }}"></
    -0.83
     Roskov
    -0.82
     AssemblyCompany
    -0.78
     فريبيس
    -0.77
    MessageOf
    -0.77
    parsedMessage
    -0.73
    KURZBESCHREIBUNG
    -0.71
     disambiguazione
    -0.71
    webElementXpaths
    -0.70
    POSITIVE LOGITS
     appeared
    0.56
     appears
    0.55
     Many
    0.51
     many
    0.50
     may
    0.50
     appear
    0.49
     is
    0.48
     becomes
    0.48
    Many
    0.46
     became
    0.46
    Activations Density 2.496%

    No Known Activations