© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3004
    Prev
    Next
    INDEX
    Explanations

    legal documents and medical 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ayaquil
    -0.60
    mybatisplus
    -0.59
     pelic
    -0.56
    дца
    -0.54
    DockStyle
    -0.50
     dinoss
    -0.49
    KommentareTeilen
    -0.49
    RequestOptions
    -0.49
    ragamo
    -0.49
    ərb
    -0.49
    POSITIVE LOGITS
     oprot
    0.58
    bitat
    0.49
    Dtor
    0.48
     Савезне
    0.48
     linkovi
    0.47
    CPtr
    0.47
    TagHelper
    0.47
    timis
    0.45
     AGB
    0.45
    хьтан
    0.44
    Activations Density 0.435%

    No Known Activations