© 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. 5174
    Prev
    Next
    INDEX
    Explanations

    a variety of proper nouns, numbers, and code-related terms.

    oai_token-act-pair · 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
    kháu
    -0.89
    UnsafeEnabled
    -0.83
     ویکی‌پدی
    -0.80
     Италијани
    -0.79
    LookAnd
    -0.78
    RegistryLite
    -0.78
    <bos>
    -0.75
     propOrder
    -0.73
     kaarangay
    -0.72
    цездатний
    -0.72
    POSITIVE LOGITS
    ſelf
    0.49
    ঢ
    0.47
     GTR
    0.47
     onStop
    0.46
     tranſ
    0.45
     sacro
    0.45
     Schot
    0.44
     Trist
    0.44
     cauſe
    0.44
     intellect
    0.44
    Activations Density 3.109%

    No Known Activations