© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1723
    Prev
    Next
    INDEX
    Explanations

    punctuation and other delimiters, occasionally near words related to dates, location, and some scientific terms

    oai_token-act-pair · gemini-2.0-flash

    measurements and units of volume and mass

    np_token-act-pair-logits · gpt-4o-mini

    measurement units

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    mobileqq
    -0.98
    jsxFileName
    -0.86
    Спасылкі
    -0.86
     وتسجيلات
    -0.85
    Personensuche
    -0.83
     سكانية
    -0.82
     &___
    -0.81
    RefNanny
    -0.78
    SharedCtor
    -0.77
     صوتيه
    -0.77
    POSITIVE LOGITS
    mm
    0.73
     mm
    0.71
    cm
    0.64
     cm
    0.64
    kg
    0.60
     kg
    0.60
    ml
    0.57
     km
    0.56
    km
    0.55
    ppm
    0.53
    Activations Density 17.030%

    No Known Activations