© 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. 3416
    Prev
    Next
    INDEX
    Explanations

    the structure of academic papers, particularly sections and how they are organized.

    oai_token-act-pair · gemini-2.0-flash

    structure

    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
    "}";
    -0.52
     vœux
    -0.51
    "]];
    -0.50
    adden
    -0.50
     préférence
    -0.49
     pitié
    -0.49
    endpush
    -0.49
    Tikang
    -0.49
    Neden
    -0.49
    醐
    -0.48
    POSITIVE LOGITS
     structure
    2.69
     Structure
    2.42
    structure
    2.34
    Structure
    2.25
     STRUCTURE
    2.19
     structures
    1.99
    结构
    1.95
    STRUCTURE
    1.93
     estructura
    1.88
     Structures
    1.79
    Activations Density 4.751%

    No Known Activations