© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4044
    Prev
    Next
    INDEX
    Explanations

    mentions of company establishment and founding dates

    oai_token-act-pair · gemini-2.0-flash

    dates of creation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    коменду
    -0.50
    AnchorStyles
    -0.49
    addTab
    -0.47
    вочка
    -0.45
    ImageIO
    -0.43
     још
    -0.43
    FormUrlEncoded
    -0.43
    数十
    -0.42
    endpush
    -0.41
     सत्यापित
    -0.41
    POSITIVE LOGITS
     vuonna
    0.87
     בשנת
    0.85
     năm
    0.83
    Year
    0.80
     Year
    0.80
     year
    0.78
     roce
    0.75
    principalTable
    0.74
     anul
    0.73
    енча
    0.71
    Activations Density 2.477%

    No Known Activations