© 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. 9469
    Prev
    Next
    INDEX
    Explanations

    the adverb "primarily", the french word parts plu/tot, and some seemingly unrelated words such as "dans".

    oai_token-act-pair · 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
     EconPapers
    -0.73
     ModelExpression
    -0.61
    VIAF
    -0.61
    SourceChecksum
    -0.60
    Viitteet
    -0.60
    Statistiche
    -0.57
    Filmographie
    -0.56
    SafeMath
    -0.55
     المعيارى
    -0.55
    XtraGrid
    -0.55
    POSITIVE LOGITS
     sẻ
    0.61
    ))->
    0.56
     سپاه
    0.51
     dehors
    0.49
     eigentlich
    0.48
     mainly
    0.48
     inkább
    0.47
    呛
    0.47
     Mainly
    0.47
     eher
    0.46
    Activations Density 1.959%

    No Known Activations