© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12691
    Prev
    Next
    INDEX
    Explanations

    code snippets from questions, specifically SQL queries and database table definitions, especially involving IDs and branches.

    oai_token-act-pair · gemini-2.0-flash

    data fields

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     propOrder
    -1.09
     AssemblyProduct
    -1.01
    Portale
    -1.01
    tagHelperRunner
    -0.97
    fjspx
    -0.94
    RenderAtEndOf
    -0.92
    RegressionTest
    -0.91
    ThroughAttribute
    -0.88
    Хьажоргаш
    -0.88
    httphttps
    -0.86
    POSITIVE LOGITS
    Number
    0.50
    Level
    0.36
    number
    0.33
    Price
    0.33
    Address
    0.33
    Time
    0.33
    Nm
    0.33
    Key
    0.32
    Meaning
    0.32
    Type
    0.31
    Activations Density 6.332%

    No Known Activations