© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9873
    Prev
    Next
    INDEX
    Explanations

    instances of abusive language or words that end in "ally"

    oai_token-act-pair · gemini-2.0-flash

    legal/abusive contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    decorate
    -0.57
     Venn
    -0.57
    LOTTE
    -0.54
     vacaciones
    -0.52
    Documented
    -0.51
    ValueStyle
    -0.50
    ֱ
    -0.50
    ează
    -0.50
     learning
    -0.49
    inars
    -0.49
    POSITIVE LOGITS
     usage
    0.69
    <bos>
    0.66
     gebruik
    0.63
     Usage
    0.60
     users
    0.59
     overuse
    0.59
     usages
    0.59
    Verwendung
    0.59
     kullanım
    0.59
     använd
    0.58
    Activations Density 0.669%

    No Known Activations