© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7938
    Prev
    Next
    INDEX
    Explanations

    words or short phrases in different languages, technical or niche subjects, or with unusual character encodings within a larger text

    oai_token-act-pair · gemini-2.0-flash

    Financial and mechanical topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     afford
    -0.60
     ever
    -0.54
     unlike
    -0.51
    ale
    -0.51
    fcc
    -0.48
    ​
    -0.47
    burgo
    -0.46
    ern
    -0.44
    違い
    -0.44
    CopyWith
    -0.44
    POSITIVE LOGITS
     myſelf
    0.78
     propOrder
    0.70
     Efq
    0.68
     RSSSF
    0.66
     juſ
    0.66
     purpoſe
    0.66
    avond
    0.66
    esterday
    0.64
     Jefus
    0.64
     auffi
    0.63
    Activations Density 5.725%

    No Known Activations