© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2879
    Prev
    Next
    INDEX
    Explanations

    instances of comparison between two groups, especially in medical analysis

    oai_token-act-pair · gemini-2.0-flash

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ORY
    -0.49
     
    -0.46
     «
    -0.45
     al
    -0.45
    ory
    -0.44
     Kim
    -0.44
     tax
    -0.44
     Tim
    -0.43
     se
    -0.42
     presented
    -0.42
    POSITIVE LOGITS
     فريبيس
    1.10
     للمعارف
    1.04
     المعيارى
    1.02
    ")));
    1.01
     propOrder
    0.98
     varandra
    0.94
     للاسماء
    0.91
    "],
    0.90
    '},
    0.86
    "},
    0.85
    Activations Density 2.162%

    No Known Activations