© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 710
    Prev
    Next
    INDEX
    Explanations

    medical or anatomical terms for conditions and body parts.

    oai_token-act-pair · gemini-2.0-flash

    Medical and bodily functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    gya
    -0.56
    はじめに
    -0.54
    isesta
    -0.51
     knock
    -0.49
     Oak
    -0.48
    Oak
    -0.48
    atur
    -0.47
     Peri
    -0.45
    jelen
    -0.45
     Knock
    -0.45
    POSITIVE LOGITS
     mouth
    0.81
     bouche
    0.75
     Mouth
    0.74
     saliva
    0.72
     tongue
    0.72
     lips
    0.71
     lèvres
    0.70
    ปาก
    0.67
     salivary
    0.67
     kasarigan
    0.67
    Activations Density 1.619%

    No Known Activations