© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13815
    Prev
    Next
    INDEX
    Explanations

    snippets of program code or budgeting 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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     prédé
    -0.50
     lourdes
    -0.49
     amélior
    -0.49
     nationales
    -0.49
     sedang
    -0.49
    δρο
    -0.48
     aproveitar
    -0.47
    umatic
    -0.47
     vendredi
    -0.47
     quelcon
    -0.47
    POSITIVE LOGITS
    uxxxx
    0.83
    WebVitals
    0.80
     calendriers
    0.73
    AsUp
    0.70
     censiti
    0.69
     يتيمه
    0.69
     TZ
    0.67
     المعيارى
    0.67
     Commencez
    0.66
    StructEnd
    0.66
    Activations Density 0.244%

    No Known Activations