© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5017
    Prev
    Next
    INDEX
    Explanations

    the phrase "to be" and other words nearby

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb "to be."

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

    to

    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
    AccessorTable
    -1.05
    setVerticalGroup
    -0.97
    verwijspagina
    -0.92
    parsedMessage
    -0.88
    NameInMap
    -0.87
     propOrder
    -0.85
    MessageOf
    -0.85
     resourceCulture
    -0.85
     otomatig
    -0.84
    DockStyle
    -0.82
    POSITIVE LOGITS
     be
    1.36
     to
    1.19
    ToBe
    0.78
     να
    0.77
    be
    0.77
    to
    0.75
    tobe
    0.74
    被
    0.71
     To
    0.66
     soient
    0.66
    Activations Density 1.624%

    No Known Activations