© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11584
    Prev
    Next
    INDEX
    Explanations

    proper nouns, names, titles, and references to specific legal proceedings

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    клопе
    -0.69
    Rujuakan
    -0.54
     Marsden
    -0.50
     kaynağından
    -0.50
     CUDA
    -0.49
     syndrome
    -0.46
     Tudo
    -0.45
     Njema
    -0.45
     MyApp
    -0.45
     UIImage
    -0.45
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.57
     LoggerFactory
    0.56
    GraphicsUnit
    0.55
    //
    0.52
     aéri
    0.52
    zade
    0.50
    حياتها
    0.50
    Cyfeiriadau
    0.50
     OBITUARY
    0.49
    τερα
    0.49
    Activations Density 1.250%

    No Known Activations