© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10184
    Prev
    Next
    INDEX
    Explanations

    positive statements saying they are excited or delighted to do things

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    Negative Logits
    RectangleBorder
    -0.63
    ibrill
    -0.49
    hadiran
    -0.47
    Personality
    -0.44
    arxiv
    -0.44
    Биография
    -0.43
     Keeping
    -0.42
     Letras
    -0.41
     сме
    -0.41
    Och
    -0.41
    POSITIVE LOGITS
    ReusableCell
    0.69
    MessageTagHelper
    0.62
    yntaxException
    0.60
    TintMode
    0.59
    ModelAdmin
    0.59
    StandardCharsets
    0.57
    HandleFunc
    0.57
    AddHtmlAttribute
    0.55
    AutoField
    0.55
    ConverterFactory
    0.55
    Activations Density 0.563%

    No Known Activations