© 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. 9356
    Prev
    Next
    INDEX
    Explanations

    words related to communities, ethnicities, and global standards

    oai_token-act-pair · gemini-2.0-flash

    nationalities and international

    np_max-act · gemini-2.0-flash

    say "leading space" Method used: 2 — tokens mostly start with a leading space

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
    Negative Logits
    annica
    -0.59
    namentales
    -0.53
     Pyrr
    -0.51
    piac
    -0.50
     Strick
    -0.50
    AppCompatTheme
    -0.50
    šnje
    -0.49
    MethodManager
    -0.48
    xically
    -0.47
     sva
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.83
    Rüyada
    0.73
    )))));
    0.70
    Brainz
    0.65
    IntoConstraints
    0.65
    PropertyChanging
    0.63
    PerformLayout
    0.63
    AccessorTable
    0.62
    oa̍t
    0.62
    hadiran
    0.60
    Activations Density 0.741%

    No Known Activations