© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14450
    Prev
    Next
    INDEX
    Explanations

    negative sentiments about wealthy people

    oai_token-act-pair · gemini-2.0-flash

    wealthy/rich people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     rich
    -2.86
     Rich
    -2.61
    Rich
    -2.59
    rich
    -2.41
     richer
    -2.36
     richest
    -2.31
     RICH
    -2.30
     riche
    -2.27
     richness
    -2.20
    RICH
    -2.03
    POSITIVE LOGITS
     novi
    0.40
    invalidate
    0.39
    cassert
    0.39
    AutoresizingMask
    0.38
    soort
    0.36
    ätzung
    0.36
    ını
    0.35
    du
    0.34
    ör
    0.34
    SqlSession
    0.33
    Activations Density 1.763%

    No Known Activations