© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5125
    Prev
    Next
    INDEX
    Explanations

    German sentences that use a lot of verbs and commas in a complex construction.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    asymp
    -0.57
    Malley
    -0.57
    msford
    -0.54
    roppo
    -0.54
     reck
    -0.52
    matum
    -0.52
    thel
    -0.52
     Nomin
    -0.50
     Lombardo
    -0.50
    στημα
    -0.49
    POSITIVE LOGITS
    expandindo
    0.68
    webElementXpaths
    0.65
    GraphicsUnit
    0.57
    pushFollow
    0.56
    SequentialGroup
    0.55
     AssemblyProduct
    0.55
     ویکی‌پدیا
    0.55
    WriteTagHelper
    0.51
    __(/*!
    0.51
    ImageContext
    0.51
    Activations Density 0.828%

    No Known Activations