© 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. 13820
    Prev
    Next
    INDEX
    Explanations

    phrases describing personal injury, medical treatment, or medical conditions.

    oai_token-act-pair · gemini-2.0-flash

    medical issues or injuries

    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
    AndEndTag
    -0.85
    ContentAsync
    -0.65
    原始内容存档于
    -0.65
    OGND
    -0.60
    ruptedException
    -0.56
    RectangleBorder
    -0.55
    PerformLayout
    -0.54
    ۇ
    -0.53
    ()}>
    -0.52
    อาด
    -0.52
    POSITIVE LOGITS
    новниш
    0.85
     препратки
    0.63
    Démographie
    0.59
    zegorz
    0.55
    farin
    0.54
     arm
    0.54
     Walkover
    0.53
    nemia
    0.52
    kháu
    0.52
     ResourceManager
    0.50
    Activations Density 2.195%

    No Known Activations