© 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. 1721
    Prev
    Next
    INDEX
    Explanations

    references to law and legal documents

    oai_token-act-pair · gemini-2.0-flash

    unusual names or phrases

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

    legal documents and code

    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
    tagHelperRunner
    -0.59
    存于互联网档案馆
    -0.57
     counters
    -0.51
     متعلقه
    -0.50
    ="#">
    -0.49
     Counters
    -0.48
     ThemeData
    -0.48
     ground
    -0.48
    Morfologia
    -0.47
    émon
    -0.46
    POSITIVE LOGITS
     
    0.69
    onActivityResult
    0.55
    squid
    0.54
    lusconi
    0.49
    lapia
    0.48
     Schnee
    0.45
    adpleegd
    0.45
     smtplib
    0.44
    نجليزية
    0.44
    ronpa
    0.44
    Activations Density 5.883%

    No Known Activations