© 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. 5876
    Prev
    Next
    INDEX
    Explanations

    words that connect one thing to another

    oai_token-act-pair · gemini-2.0-flash

    Business and organizations

    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
    NameInMap
    -0.70
    providedIn
    -0.67
    ListItemIcon
    -0.62
     combineReducers
    -0.61
    XmlAccessType
    -0.60
    FXML
    -0.57
     ApiException
    -0.57
    
    -0.56
    initComponents
    -0.56
    Reducers
    -0.56
    POSITIVE LOGITS
     growth
    0.54
    <bos>
    0.53
    셨
    0.51
    λου
    0.48
     nahilalakip
    0.48
    DebuggerNonUser
    0.47
     gainera
    0.45
    QUIN
    0.45
     sale
    0.44
    quième
    0.44
    Activations Density 2.527%

    No Known Activations