© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3698
    Prev
    Next
    INDEX
    Explanations

    words related to school, learning, comprehension, and children's activities

    oai_token-act-pair · gemini-2.0-flash

    words related to games and applications

    np_token-act-pair-logits · gpt-4o-mini

    apps and 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    MigrationBuilder
    -0.81
     intptr
    -0.66
     autorytatywna
    -0.60
    hradun
    -0.56
    IntoConstraints
    -0.56
     cherchés
    -0.55
    tonode
    -0.54
    :✨
    -0.53
     hagas
    -0.52
    XmlAccessorType
    -0.51
    POSITIVE LOGITS
     games
    0.71
     apps
    0.68
     GAMES
    0.59
    games
    0.58
     Games
    0.56
    apps
    0.56
    Games
    0.56
     Apps
    0.55
     counted
    0.54
     app
    0.54
    Activations Density 3.757%

    No Known Activations