© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4534
    Prev
    Next
    INDEX
    Explanations

    the word "compare" and its variations.

    oai_token-act-pair · gemini-2.0-flash

    compare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     comparison
    -2.55
     compare
    -2.41
     comparing
    -2.25
     Comparison
    -2.25
     compares
    -2.19
    comparison
    -2.14
    compare
    -2.14
    Comparison
    -2.11
     comparisons
    -2.11
    Compare
    -2.09
    POSITIVE LOGITS
     CreateTagHelper
    0.85
    esModule
    0.72
     useStyles
    0.66
     rospy
    0.64
    icach
    0.60
    󠁢
    0.59
     MainAxisSize
    0.58
    !*\
    0.58
    initState
    0.55
    Trama
    0.54
    Activations Density 0.432%

    No Known Activations