© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15863
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and academic study

    oai_token-act-pair · gemini-2.0-flash

    science/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    RenderAtEndOf
    -0.79
     виправивши
    -0.77
    KommentareTeilen
    -0.73
    ‘‘
    -0.72
    BeginInit
    -0.71
    Hentet
    -0.71
     AssemblyCulture
    -0.70
    . 
    -0.69
    PhysRevD
    -0.68
     >=",
    -0.68
    POSITIVE LOGITS
    Whilst
    0.80
     Whilst
    0.77
     whilst
    0.77
     diatas
    0.62
     perchè
    0.60
     Ministre
    0.57
     poichè
    0.52
     amongst
    0.49
     Amongst
    0.47
     AssemblyTitle
    0.46
    Activations Density 2.958%

    No Known Activations