© 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. 9623
    Prev
    Next
    INDEX
    Explanations

    array-related code elements, especially instantiation and appending in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    code syntax brackets

    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
    q
    -0.56
    ij
    -0.46
     es
    -0.46
     Q
    -0.44
    SceneManagement
    -0.44
    Q
    -0.43
    нг
    -0.42
    application
    -0.42
     mi
    -0.42
     there
    -0.42
    POSITIVE LOGITS
     Theſe
    0.91
     myſelf
    0.84
     Majefty
    0.80
     ſeveral
    0.79
     houſe
    0.75
     Monfieur
    0.75
     whoſe
    0.74
     Jefus
    0.73
     theſe
    0.73
     againſt
    0.73
    Activations Density 0.738%

    No Known Activations