© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11131
    Prev
    Next
    INDEX
    Explanations

    descriptive language about research methodology, including performing experiments, providing a comparison, and offering theoretical results

    oai_token-act-pair · gemini-2.0-flash

    scientific experiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    SourceChecksum
    -0.95
     GenerationType
    -0.93
    EDEFAULT
    -0.73
    XmlAccessType
    -0.73
    :✨
    -0.72
     للمعارف
    -0.71
    fjspx
    -0.71
    ArgumentParser
    -0.70
     utafitiHapana
    -0.68
    complexContent
    -0.67
    POSITIVE LOGITS
     initComponents
    0.52
     autorytatywna
    0.44
    xase
    0.43
    VEST
    0.41
     NSError
    0.40
    NSError
    0.40
     ElementRef
    0.37
    多少
    0.36
     Wall
    0.36
    مصادر
    0.35
    Activations Density 9.958%

    No Known Activations