© 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. 15231
    Prev
    Next
    INDEX
    Explanations

    fragments of programming code

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    <bos>
    -0.83
     CallOverrides
    -0.77
     propOrder
    -0.70
    Personendaten
    -0.68
    makeConstraints
    -0.68
    openzeppelin
    -0.68
    enterOuterAlt
    -0.67
     cherchés
    -0.67
     AssemblyVersion
    -0.66
    UnusedPrivate
    -0.65
    POSITIVE LOGITS
     referenties
    0.41
    CloseOperation
    0.37
    Xaml
    0.36
    //
    0.35
    <h4>
    0.35
     geb
    0.35
    <
    0.34
    [
    0.33
     dolorosa
    0.32
    ###
    0.32
    Activations Density 0.132%

    No Known Activations