© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12757
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the immune system and its function

    oai_token-act-pair · gemini-2.0-flash

    immune

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     myſelf
    -0.70
    RTGC
    -0.62
     تضيفلها
    -0.61
     whoſe
    -0.60
     ModelExpression
    -0.60
     themſelves
    -0.60
    ApiModelProperty
    -0.60
     oprot
    -0.59
    featureID
    -0.59
     autorytatywna
    -0.59
    POSITIVE LOGITS
     system
    0.57
    full
    0.53
     System
    0.45
     glyphicon
    0.45
    System
    0.45
     full
    0.45
    system
    0.44
    zal
    0.43
    sur
    0.41
    システム
    0.41
    Activations Density 1.898%

    No Known Activations