© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11389
    Prev
    Next
    INDEX
    Explanations

    mentions of humor and jokes, and people taking a role with humorous characteristics.

    oai_token-act-pair · gemini-2.0-flash

    humor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     laugh
    -2.34
     humor
    -2.14
     funny
    -2.14
     laughs
    -2.13
     laughing
    -2.13
     laughed
    -2.11
     laughter
    -2.06
     humorous
    -2.06
     joke
    -2.03
     humour
    -2.00
    POSITIVE LOGITS
     Oso
    0.47
    getDescriptor
    0.46
     Arag
    0.46
     Supremo
    0.43
     impré
    0.43
     Hyatt
    0.42
     Paramètres
    0.42
     Streptococcus
    0.41
    ichen
    0.40
     دیکھیے
    0.40
    Activations Density 1.124%

    No Known Activations