© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11671
    Prev
    Next
    INDEX
    Explanations

    code snippets involving variables and execution

    oai_token-act-pair · gemini-2.0-flash

    code and legal texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    RegressionTest
    -0.75
    IVEREF
    -0.65
    BufferException
    -0.61
     بيها
    -0.57
    ChildScrollView
    -0.57
     يتيمه
    -0.56
    Espèce
    -0.56
    انجليز
    -0.55
    Rhestr
    -0.55
    hmig
    -0.54
    POSITIVE LOGITS
     transfieras
    0.53
     **/
    0.53
     paff
    0.50
     Hanover
    0.47
    nodoc
    0.46
     Trojan
    0.45
     CHP
    0.45
     Urbano
    0.45
     consommation
    0.45
     Nestlé
    0.44
    Activations Density 2.655%

    No Known Activations