© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11612
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code/memory regions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    IUrlHelper
    -0.75
    endphp
    -0.73
     Référence
    -0.64
    WithMany
    -0.62
     EconPapers
    -0.61
    setVerticalGroup
    -0.59
    rrggbb
    -0.59
     saites
    -0.59
    ViewImports
    -0.58
    tanleria
    -0.58
    POSITIVE LOGITS
    ServiceModel
    0.56
    Facades
    0.52
    #__
    0.50
    sdl
    0.47
    FAC
    0.45
     AAC
    0.44
    /**/*.
    0.44
    ssi
    0.44
    kne
    0.43
    AAC
    0.43
    Activations Density 1.591%

    No Known Activations