© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6197
    Prev
    Next
    INDEX
    Explanations

    the phrase "with respect to"

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     respect
    -1.06
     respecting
    -1.03
    respect
    -1.03
     respects
    -1.00
     regards
    -0.98
     regard
    -0.91
     Respect
    -0.87
     rispetto
    -0.86
    Respect
    -0.84
    regard
    -0.81
    POSITIVE LOGITS
     res
    0.61
    QMetaType
    0.60
    tadır
    0.56
     re
    0.55
    IContainer
    0.54
     jScrollPane
    0.54
     reg
    0.52
     AssemblyCulture
    0.51
     للاسماء
    0.50
    estacks
    0.49
    Activations Density 1.619%

    No Known Activations