© 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. 13981
    Prev
    Next
    INDEX
    Explanations

    the word "as" followed by "to" in the context of legal disputes and evidence

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating comparisons or relationships

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

    as

    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
     kasarigan
    -1.01
    ValueStyle
    -0.94
    expandindo
    -0.94
    RenderAtEndOf
    -0.85
    ंदीखरीदारी
    -0.84
    ConstraintMaker
    -0.81
     مشين
    -0.81
    PerformLayout
    -0.80
    LookAnd
    -0.78
    ыгана
    -0.76
    POSITIVE LOGITS
     to
    0.69
     προς
    0.57
     regards
    0.56
    to
    0.54
    дра
    0.49
    contentPane
    0.47
    intérêt
    0.47
     compared
    0.47
     entre
    0.44
    ph
    0.44
    Activations Density 1.404%

    No Known Activations