© 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. 9689
    Prev
    Next
    INDEX
    Explanations

    words that are part of scientific studies or analyses

    oai_token-act-pair · gemini-2.0-flash

    analysis

    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
     saying
    -0.51
     Saying
    -0.48
    saying
    -0.47
    getter
    -0.45
    วา
    -0.43
     falar
    -0.43
     says
    -0.43
     conduct
    -0.42
    amata
    -0.42
    Concepto
    -0.42
    POSITIVE LOGITS
    //
    0.70
    awtextra
    0.68
    expandindo
    0.65
     initComponents
    0.64
     AssemblyCompany
    0.64
    \{\\
    0.63
    SourceChecksum
    0.63
     delivered
    0.62
    EndInit
    0.60
     served
    0.60
    Activations Density 4.535%

    No Known Activations