© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6510
    Prev
    Next
    INDEX
    Explanations

    the digit '2' followed by one or two additional numbers such as a year

    oai_token-act-pair · gemini-2.0-flash

    year 2020

    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
     AssemblyTitle
    -0.76
    ViewImports
    -0.69
     kasarigan
    -0.63
    
    -0.57
    __':
    -0.57
    JspWriter
    -0.57
     дописавши
    -0.56
    ectl
    -0.56
    期刊论文
    -0.54
    mybatisplus
    -0.53
    POSITIVE LOGITS
     Bourgoin
    0.56
     externi
    0.54
     gostar
    0.51
     ordine
    0.51
    LookAnd
    0.50
    มาะ
    0.49
     Siamo
    0.49
     mohair
    0.49
     farmacé
    0.49
     кислота
    0.49
    Activations Density 0.211%

    No Known Activations