© 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. 11668
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "it is" or "it's."

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating uncertainty

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

    it

    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
     AssemblyCulture
    -0.78
    AddTagHelper
    -0.77
    ScopeManager
    -0.77
     Theſe
    -0.75
     itſelf
    -0.73
    rungsseite
    -0.71
     ModelExpression
    -0.70
     themſelves
    -0.70
    its
    -0.69
    AddHtmlAttribute
    -0.68
    POSITIVE LOGITS
     it
    0.56
     appear
    0.52
     appears
    0.50
    #+#
    0.50
    appears
    0.48
    WindowConstants
    0.48
    appear
    0.47
     appeared
    0.47
     APPE
    0.45
    getDescriptor
    0.45
    Activations Density 0.354%

    No Known Activations