© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13418
    Prev
    Next
    INDEX
    Explanations

    instances of things being funny (humor, laughing, etc.) .

    oai_token-act-pair · gemini-2.0-flash

    funny

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     greateſt
    -0.99
    ſelf
    -0.96
     snippetHide
    -0.94
    ſelves
    -0.94
     المعيارى
    -0.91
     houſe
    -0.86
    neſs
    -0.85
    IntoConstraints
    -0.84
     ſtate
    -0.82
     Majefty
    -0.81
    POSITIVE LOGITS
    <bos>
    0.59
     of
    0.52
    “
    0.45
     in
    0.45
    .
    0.42
    *
    0.42
    ,
    0.41
    we
    0.41
    vers
    0.41
    M
    0.41
    Activations Density 0.593%

    No Known Activations