© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4934
    Prev
    Next
    INDEX
    Explanations

    words associated with criminal acts, future events, and groups of people

    oai_token-act-pair · gemini-2.0-flash

    Illicit activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     resourceCulture
    -0.84
    PreferredItem
    -0.79
    تقاوى
    -0.79
    AddHtmlAttribute
    -0.77
     виправивши
    -0.71
    ConstraintMaker
    -0.69
    SequentialGroup
    -0.67
    IsUnicode
    -0.66
    RegressionTest
    -0.66
    InfoWindow
    -0.66
    POSITIVE LOGITS
    stander
    0.39
     پلیس
    0.38
     mengeluarkan
    0.38
    SetDefault
    0.36
    Abp
    0.36
    ñera
    0.36
    balanceOf
    0.36
     mỗi
    0.36
    guera
    0.36
    uve
    0.35
    Activations Density 49.705%

    No Known Activations