© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8903
    Prev
    Next
    INDEX
    Explanations

    words related to jokes and trickery

    oai_token-act-pair · gemini-2.0-flash

    games

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ContentAlignment
    -0.57
    enschutzer
    -0.51
    ̍t
    -0.50
     ivelany
    -0.50
    bosis
    -0.49
    kadot
    -0.49
    größern
    -0.48
    idist
    -0.48
    arnished
    -0.48
    Бахар
    -0.48
    POSITIVE LOGITS
     games
    1.50
     game
    1.43
    game
    1.30
     Games
    1.29
    Games
    1.27
     GAMES
    1.23
     giochi
    1.20
    Game
    1.20
     gioco
    1.20
    games
    1.20
    Activations Density 1.175%

    No Known Activations