© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13818
    Prev
    Next
    INDEX
    Explanations

    words with a positive or descriptive connotation

    oai_token-act-pair · gemini-2.0-flash

    Nature and science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ーキング
    -0.50
     convenient
    -0.50
     eyes
    -0.48
     transporting
    -0.46
    Absent
    -0.46
     without
    -0.45
    I
    -0.45
     personnalisés
    -0.45
     abstrato
    -0.44
    徵
    -0.44
    POSITIVE LOGITS
    uttavia
    0.84
     nahilalakip
    0.77
     mergeFrom
    0.74
    sizeCache
    0.73
    ReusableCell
    0.72
    شهاد
    0.70
    tagext
    0.68
     الرياضيه
    0.68
    ictwa
    0.64
     OFDb
    0.64
    Activations Density 0.956%

    No Known Activations