© 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. 16216
    Prev
    Next
    INDEX
    Explanations

    medical terminology, particularly in the context of patient evaluation and treatment

    oai_token-act-pair · gemini-2.0-flash

    medical texts

    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
    adaptiveStyles
    -0.92
    AutoScale
    -0.82
     Italijanski
    -0.81
     للاسماء
    -0.81
    ValueStyle
    -0.81
    Vidite
    -0.79
     nahilalakip
    -0.74
     jScrollPane
    -0.72
     &___
    -0.71
    TagMode
    -0.69
    POSITIVE LOGITS
    不定
    0.37
    pos
    0.37
     anges
    0.37
     Ephesus
    0.37
    os
    0.37
     shows
    0.37
    のだ
    0.37
    ca
    0.36
     mont
    0.36
     Her
    0.35
    Activations Density 44.637%

    No Known Activations