© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10099
    Prev
    Next
    INDEX
    Explanations

    first person pronouns, often accompanying the words "why" or "started"

    oai_token-act-pair · gemini-2.0-flash

    conversational text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pleins
    -0.45
    EXACT
    -0.44
     esattamente
    -0.43
     наи
    -0.43
     πρέπει
    -0.41
    知る
    -0.41
    v
    -0.40
     mediano
    -0.40
     Handmaid
    -0.40
     précisément
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.83
    yntaxException
    0.71
    RegressionTest
    0.70
    HtmlAttribute
    0.69
     فريبيس
    0.69
     HttpHeaders
    0.68
     betweenstory
    0.67
    rungsseite
    0.65
    تقاوى
    0.62
     ImageIcon
    0.62
    Activations Density 2.999%

    No Known Activations