© 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. 10039
    Prev
    Next
    INDEX
    Explanations

    humorous situations.

    oai_token-act-pair · gemini-2.0-flash

    humor and jokes

    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
    mtrl
    -0.71
     myſelf
    -0.70
     becauſe
    -0.70
     diſt
    -0.69
    DJANGO
    -0.65
     ſy
    -0.63
    wiſe
    -0.63
     Majefty
    -0.61
    ISupport
    -0.60
    leſs
    -0.60
    POSITIVE LOGITS
    <eos>
    0.51
    isti
    0.50
     car
    0.46
     nakalista
    0.45
     Car
    0.42
    Бахар
    0.42
     men
    0.41
     track
    0.41
     (
    0.41
    rungsseite
    0.41
    Activations Density 5.744%

    No Known Activations