© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15354
    Prev
    Next
    INDEX
    Explanations

    connectors and prepositions

    oai_token-act-pair · gemini-2.0-flash

    variations of the verb "to be"

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

    Forms of "be"

    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
    Negative Logits
    Personendaten
    -1.02
    ThroughAttribute
    -1.02
    @[+][
    -0.65
     propOrder
    -0.63
     فريبيس
    -0.63
    PreferredItem
    -0.62
    antd
    -0.61
     StatefulWidget
    -0.60
    CloseOperation
    -0.59
    setViewportView
    -0.59
    POSITIVE LOGITS
     be
    2.31
     being
    1.67
     être
    1.56
     быть
    1.51
     být
    1.48
     Be
    1.45
     бути
    1.44
     essere
    1.42
     być
    1.42
    Be
    1.41
    Activations Density 3.073%

    No Known Activations