© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3704
    Prev
    Next
    INDEX
    Explanations

    words related to chemical reactions, temperatures, and materials science

    oai_token-act-pair · gemini-2.0-flash

    Burning/combustion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ignition
    -0.69
     spark
    -0.52
     Ignition
    -0.49
     SPARK
    -0.49
     arrancar
    -0.47
    spark
    -0.46
    Ignition
    -0.44
     igni
    -0.43
     Spark
    -0.43
     fuoco
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    0.69
    \{\\
    0.69
    AutoresizingMask
    0.69
    elemField
    0.69
    NameInMap
    0.66
    +#+#
    0.60
    Aiheesta
    0.60
    }();
    0.59
    })();
    0.59
    parsedMessage
    0.58
    Activations Density 2.093%

    No Known Activations