© 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. 12698
    Prev
    Next
    INDEX
    Explanations

    instances of one person helping another and strong emotional reactions

    oai_token-act-pair · 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
    tagHelperRunner
    -0.81
     StatefulWidget
    -0.78
     تضيفلها
    -0.70
     StatelessWidget
    -0.68
     NavController
    -0.67
    GTCX
    -0.66
    httphttps
    -0.65
     ſind
    -0.63
     myſelf
    -0.62
     tartalomajánló
    -0.61
    POSITIVE LOGITS
    WriteTagHelper
    0.50
     this
    0.48
     переписи
    0.47
     AttributeSet
    0.46
     the
    0.46
    modelBuilder
    0.43
    makeText
    0.43
     other
    0.41
     them
    0.41
     a
    0.41
    Activations Density 1.004%

    No Known Activations