© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11986
    Prev
    Next
    INDEX
    Explanations

    HTML code snippets

    oai_token-act-pair · gemini-2.0-flash

    code</code>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <code>
    -2.42
     fubject
    -0.84
     مشين
    -0.79
    ViewFeatures
    -0.75
     Reſ
    -0.73
    ^(@)
    -0.72
    abstractmethod
    -0.72
    </caption>
    -0.71
     initComponents
    -0.71
     poffe
    -0.70
    POSITIVE LOGITS
     buat
    0.44
    راسیون
    0.43
     i
    0.42
    ècie
    0.42
    DoubleQuotes
    0.42
    build
    0.42
    ↵
    0.42
    wachs
    0.41
    la
    0.41
    ti
    0.40
    Activations Density 1.329%

    No Known Activations