© 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. 3791
    Prev
    Next
    INDEX
    Explanations

    words related to soccer and sports teams, as well as the names of places and people involved in such activities.

    oai_token-act-pair · gemini-2.0-flash

    international soccer

    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
    ConstraintMaker
    -0.81
     unknownFields
    -0.75
    InvalidProtocol
    -0.75
    webElementXpaths
    -0.74
    quelize
    -0.73
    toHaveBeen
    -0.67
    StoryboardSegue
    -0.65
     FileNotFound
    -0.64
     propOrder
    -0.64
    󠁢
    -0.63
    POSITIVE LOGITS
    OGND
    0.56
    jface
    0.51
    phy
    0.43
    View
    0.43
    ϊ
    0.41
     esterni
    0.40
     adaptarse
    0.39
    interface
    0.38
     Hill
    0.37
    ợt
    0.36
    Activations Density 13.597%

    No Known Activations