© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14219
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by articles, and often preceded by other words or phrases.

    oai_token-act-pair · gemini-2.0-flash

    code sections

    np_max-act-logits · 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
     in
    -0.92
     kasarigan
    -0.86
    RenderAtEndOf
    -0.66
     Wikimedijinoj
    -0.62
     rayures
    -0.61
    AndEndTag
    -0.61
     referenties
    -0.60
     commerciaux
    -0.60
    InBackground
    -0.58
     ویکی‌پدیای
    -0.57
    POSITIVE LOGITS
     locks
    0.58
    NgModule
    0.52
    lowns
    0.52
    Спољашње
    0.51
     poveznice
    0.50
    galus
    0.50
     musical
    0.49
     analogy
    0.49
     bulk
    0.48
    gnancy
    0.48
    Activations Density 1.079%

    No Known Activations