© 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. 6786
    Prev
    Next
    INDEX
    Explanations

    instances of the word "compared"

    oai_token-act-pair · gemini-2.0-flash

    compared

    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
    AddTagHelper
    -1.03
    ValueStyle
    -1.00
    ConstraintMaker
    -0.94
     nakalista
    -0.94
    __':
    -0.92
    __":
    -0.88
    BagLayout
    -0.88
    InputBorder
    -0.86
    PerformLayout
    -0.85
    Hochspringen
    -0.85
    POSITIVE LOGITS
     to
    1.09
     with
    1.01
     avec
    0.70
    with
    0.59
     With
    0.59
     I
    0.57
    to
    0.55
    With
    0.52
      
    0.52
     f
    0.50
    Activations Density 6.340%

    No Known Activations