© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15490
    Prev
    Next
    INDEX
    Explanations

    biological and medical research papers focused on damage, disorders, and treatments

    oai_token-act-pair · gemini-2.0-flash

    technical terms and references in data or coding contexts

    np_token-act-pair-logits · gpt-4o-mini

    genetics and inner ear disorders

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ربای
    -0.56
     Rollo
    -0.52
     Freud
    -0.50
     ModelRenderer
    -0.50
     psychic
    -0.48
     viſ
    -0.48
     gynhyrchwyd
    -0.48
     المعرف
    -0.47
    AndroidJUnit
    -0.47
     CascadeType
    -0.47
    POSITIVE LOGITS
    NameInMap
    0.75
    __":
    0.61
     referenties
    0.60
    EndContext
    0.58
     незавершена
    0.58
    bootstrapcdn
    0.57
    ukone
    0.56
    /******/
    0.52
     mergeFrom
    0.52
    جستارهای
    0.51
    Activations Density 1.925%

    No Known Activations