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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4420
    Prev
    Next
    INDEX
    Explanations

    medical or dental topics being discussed in some form

    oai_token-act-pair · gemini-2.0-flash

    Family and medical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     vang
    -0.52
    Clik
    -0.52
    IonicModule
    -0.52
    存于互联网档案馆
    -0.52
    زد
    -0.50
    IVEREF
    -0.48
     referenties
    -0.48
     оригіналу
    -0.47
    âtel
    -0.47
    <table>
    -0.46
    POSITIVE LOGITS
     practice
    0.77
    practice
    0.70
     Practice
    0.67
     practise
    0.65
     household
    0.61
     marriage
    0.60
     PRACTICE
    0.60
    Practice
    0.60
    household
    0.59
    PRACTICE
    0.56
    Activations Density 6.002%

    No Known Activations