© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9385
    Prev
    Next
    INDEX
    Explanations

    the word "relative" used in scientific or technical contexts

    oai_token-act-pair · gemini-2.0-flash

    relative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     дописавши
    -0.96
    awtextra
    -0.94
     AssemblyTitle
    -0.86
     initComponents
    -0.82
    CloseOperation
    -0.81
    ukone
    -0.79
     propOrder
    -0.78
     CURIAM
    -0.78
    onOptions
    -0.77
     surla
    -0.77
    POSITIVE LOGITS
    3
    0.61
     onAnimation
    0.56
    ium
    0.56
    es
    0.56
    1
    0.55
    y
    0.54
    ytt
    0.54
    2
    0.53
    7
    0.52
    yp
    0.50
    Activations Density 1.010%

    No Known Activations