© 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. 5160
    Prev
    Next
    INDEX
    Explanations

    text discussing the start of the school year

    oai_token-act-pair · gemini-2.0-flash

    start of school year

    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
    Autoritní
    -0.67
     disambiguazione
    -0.62
    :✨
    -0.61
     resourceCulture
    -0.59
    تقاوى
    -0.58
    eleste
    -0.52
     NavController
    -0.50
    élien
    -0.49
    protoc
    -0.48
    ErrorListener
    -0.47
    POSITIVE LOGITS
    ablon
    0.54
    principalColumn
    0.54
    anaf
    0.51
    tagHelper
    0.51
    таратура
    0.51
     nost
    0.50
     duod
    0.50
    InputTagHelper
    0.50
    HasAnnotation
    0.49
     FishBase
    0.49
    Activations Density 1.594%

    No Known Activations