© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14413
    Prev
    Next
    INDEX
    Explanations

    parentheses at the beginning of code or equation snippets

    oai_token-act-pair · gemini-2.0-flash

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     <",
    -0.93
     nakalista
    -0.91
     kasarigan
    -0.89
    IVEREF
    -0.83
    lccn
    -0.83
    MethodManager
    -0.81
     EconPapers
    -0.81
    RenderAtEndOf
    -0.80
     CreateTagHelper
    -0.80
    endphp
    -0.77
    POSITIVE LOGITS
    len
    0.45
    pi
    0.45
     Max
    0.42
    тт
    0.42
    py
    0.40
     a
    0.39
    jo
    0.38
    ,
    0.38
    gos
    0.38
     degree
    0.38
    Activations Density 4.144%

    No Known Activations