© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15789
    Prev
    Next
    INDEX
    Explanations

    seemingly random open and close parenthesis and curly braces, perhaps related to code structure

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    PerformLayout
    -0.63
    lapsingToolbar
    -0.63
    LinkId
    -0.58
    casian
    -0.57
    MessageTagHelper
    -0.57
    ItemBackground
    -0.55
    CastException
    -0.55
    insee
    -0.55
     INSEE
    -0.54
    polator
    -0.54
    POSITIVE LOGITS
    awaiter
    0.54
    (!__
    0.53
     ```
    0.53
     initComponents
    0.52
    principalColumn
    0.52
    ```
    0.51
    )__
    0.49
    IsContent
    0.48
     "");
    0.47
     "__
    0.47
    Activations Density 1.955%

    No Known Activations