© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4412
    Prev
    Next
    INDEX
    Explanations

    mentions of video games

    oai_token-act-pair · gemini-2.0-flash

    Video 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Boltzmann
    -0.56
     useAuth
    -0.56
    PreferredItem
    -0.55
     WebDriverWait
    -0.54
    AccessorTable
    -0.53
     parapet
    -0.53
     שוליים
    -0.52
    SearchTree
    -0.51
     Buses
    -0.51
     Trains
    -0.50
    POSITIVE LOGITS
     esternos
    0.59
    достатки
    0.49
    Ārējās
    0.48
    paravant
    0.47
    )++;
    0.46
    expandindo
    0.44
    InjectAttribute
    0.44
    IDENTAL
    0.43
    rettet
    0.43
    ghest
    0.42
    Activations Density 0.525%

    No Known Activations