© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9326
    Prev
    Next
    INDEX
    Explanations

    terms and phrases used in legal and academic writing and in scientific reports

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     her
    -0.60
     the
    -0.58
     ContentValues
    -0.56
    новниш
    -0.54
     so
    -0.52
     and
    -0.50
     SqlParameter
    -0.50
    ]<=
    -0.50
     “
    -0.49
    </em>
    -0.49
    POSITIVE LOGITS
     himſelf
    0.81
     itſelf
    0.80
     Efq
    0.72
     themſelves
    0.72
     ujednoznacz
    0.69
     <>",
    0.68
     Ptolemy
    0.67
     TZ
    0.66
     AssemblyCompany
    0.66
     comets
    0.65
    Activations Density 30.551%

    No Known Activations