© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2363
    Prev
    Next
    INDEX
    Explanations

    code and programming terms in multiple languages

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash

    words or phrases in multiple languages

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    VersionUID
    -0.63
     Sloveniji
    -0.55
     por
    -0.50
     lucru
    -0.49
     fapt
    -0.48
     GenerationType
    -0.48
    RegressionTest
    -0.47
     partea
    -0.47
    Por
    -0.46
    CodeAttribute
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.79
    :✨
    0.77
    ToProps
    0.71
    WriteTagHelper
    0.71
    GEBURTSDATUM
    0.68
     StatefulWidget
    0.61
     viewDidLoad
    0.58
    UseVisualStyle
    0.57
     Boul
    0.57
     Extension
    0.56
    Activations Density 0.378%

    No Known Activations