© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15852
    Prev
    Next
    INDEX
    Explanations

    names of cities and sports teams

    oai_token-act-pair · gemini-2.0-flash

    city names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    IntoConstraints
    -0.88
    MENAFN
    -0.80
    DoubleQuotes
    -0.80
    encodeWith
    -0.79
    mapStateToProps
    -0.78
    )++;
    -0.68
    ChildScrollView
    -0.67
    InstanceState
    -0.66
    Климат
    -0.66
    }}],
    -0.65
    POSITIVE LOGITS
    hermes
    0.55
    FailureListener
    0.50
    améli
    0.50
    lucas
    0.47
    mutlich
    0.47
     ResourceManager
    0.44
    烤
    0.43
     jullie
    0.42
    entrySet
    0.41
    arschijnlijk
    0.41
    Activations Density 9.355%

    No Known Activations