© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5162
    Prev
    Next
    INDEX
    Explanations

    words related to medical procedures and body parts

    oai_token-act-pair · gemini-2.0-flash

    bodily fluids/medical context

    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
    كتب
    -0.47
     اعتماد
    -0.40
     Offizielle
    -0.40
    ГЛА
    -0.40
     basah
    -0.39
     fortsatt
    -0.39
     húmedo
    -0.39
    енча
    -0.38
     viết
    -0.37
     populaires
    -0.36
    POSITIVE LOGITS
     EconPapers
    0.92
     مشين
    0.87
    
    0.86
     CreateTagHelper
    0.83
    ModelSerializer
    0.75
    ftagPool
    0.73
    RenderAtEndOf
    0.70
    oa̍t
    0.69
    SceneManagement
    0.68
     hadi
    0.67
    Activations Density 2.260%

    No Known Activations