© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6084
    Prev
    Next
    INDEX
    Explanations

    words related to academic research and reporting

    oai_token-act-pair · gemini-2.0-flash

    Systems

    np_max-act-logits · 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
    Not in Any Lists

    No Comments

    Negative Logits
     Obrigado
    -0.52
     fernández
    -0.51
     pão
    -0.49
     eccl
    -0.49
     eiffel
    -0.49
     köln
    -0.49
     auffi
    -0.49
     marseille
    -0.48
     Pourquoi
    -0.48
     pegat
    -0.47
    POSITIVE LOGITS
     System
    0.88
     Field
    0.88
     Station
    0.81
     Line
    0.80
     Service
    0.79
     Site
    0.79
     Collection
    0.79
     Box
    0.79
     Report
    0.78
     Fund
    0.78
    Activations Density 8.905%

    No Known Activations