© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2725
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific studies and measurements

    oai_token-act-pair · gemini-2.0-flash

    experimental conditions

    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
    Negative Logits
    SBATCH
    -0.65
     resourceCulture
    -0.62
     CWE
    -0.60
    олові
    -0.59
     MediatR
    -0.58
    HtmlAttribute
    -0.58
    ﷺ
    -0.57
    ]='\
    -0.56
     getRule
    -0.56
    ComponentScan
    -0.54
    POSITIVE LOGITS
     온
    0.44
     script
    0.43
     irradiation
    0.43
    INCREF
    0.43
    sor
    0.43
    ppon
    0.42
    celand
    0.41
    GenerationType
    0.41
     values
    0.41
     lang
    0.41
    Activations Density 7.135%

    No Known Activations