© 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. 1416
    Prev
    Next
    INDEX
    Explanations

    phrases involving medical procedures, treatment plans, and doctor's intentions

    oai_token-act-pair · gemini-2.0-flash

    treat/Treatment

    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
    MigrationBuilder
    -0.57
     Wikimedijinoj
    -0.54
    UnusedPrivate
    -0.50
     Player
    -0.50
     Khu
    -0.48
    躇
    -0.47
    PreferredItem
    -0.47
    BURGH
    -0.47
    Player
    -0.46
    AndEndTag
    -0.46
    POSITIVE LOGITS
     treat
    0.78
     Treat
    0.76
     TREAT
    0.75
     treated
    0.75
     treating
    0.69
    Treat
    0.65
    InvalidProtocol
    0.64
     treats
    0.63
    treat
    0.62
    TREAT
    0.60
    Activations Density 4.135%

    No Known Activations