© 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. 12468
    Prev
    Next
    INDEX
    Explanations

    sentences or clauses about football player injuries

    oai_token-act-pair · gemini-2.0-flash

    Football players/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
     couverts
    -0.53
     cliquant
    -0.50
     taza
    -0.49
     affitto
    -0.49
    VersionUID
    -0.45
     neutre
    -0.44
    tikus
    -0.42
     épaules
    -0.42
     vectorielles
    -0.42
    endregion
    -0.42
    POSITIVE LOGITS
     विश्वसनीयता
    0.85
    parsedMessage
    0.72
     disambiguazione
    0.72
    onAttach
    0.65
     RemoteException
    0.65
     חיצוניים
    0.63
    kháu
    0.61
     defaultstate
    0.61
    ViewImports
    0.60
     Blocking
    0.60
    Activations Density 1.547%

    No Known Activations