© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12135
    Prev
    Next
    INDEX
    Explanations

    passages describing repetitive processes or hierarchical structures

    oai_token-act-pair · gemini-2.0-flash

    Repeating processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     réguli
    -0.56
     atuação
    -0.55
     Contin
    -0.55
    Bioaccumulative
    -0.55
    Viitteet
    -0.54
    ProgressHUD
    -0.53
     schermo
    -0.53
    iries
    -0.52
     scherm
    -0.52
    GraphicsUnit
    -0.52
    POSITIVE LOGITS
    ConstraintMaker
    0.56
     بيها
    0.52
    Źródło
    0.51
    expandindo
    0.50
    Extinguishing
    0.50
    Hentet
    0.50
    IFO
    0.49
    cheme
    0.49
    ChromeDriver
    0.49
     ivelany
    0.47
    Activations Density 2.234%

    No Known Activations