© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11245
    Prev
    Next
    INDEX
    Explanations

    words related to medicine or data analysis, specifically in the context of a study or surgical procedures

    oai_token-act-pair · gemini-2.0-flash

    medicine/medical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     InputDecoration
    -0.56
    ctical
    -0.53
     disponibilités
    -0.53
    omeness
    -0.52
    getAs
    -0.52
     tournoi
    -0.51
    __(/*!
    -0.50
     kasarigan
    -0.49
    حوالہ
    -0.48
    mentaux
    -0.47
    POSITIVE LOGITS
     متعلقه
    0.79
    enumi
    0.74
    mybatisplus
    0.65
    apimachinery
    0.64
    tagHelperRunner
    0.58
    tvguidetime
    0.57
    ))^
    0.52
     intStringLen
    0.51
     ivelany
    0.49
     motion
    0.49
    Activations Density 2.578%

    No Known Activations