© 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. 15373
    Prev
    Next
    INDEX
    Explanations

    terms related to e-commerce or electronic business

    oai_token-act-pair · gemini-2.0-flash

    e-commerce terms or patterns

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

    e-commerce and e-mail

    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
    OGND
    -0.73
    __':
    -0.72
    getMenuInflater
    -0.62
    AndEndTag
    -0.56
    TypedDataSet
    -0.55
    Gön
    -0.54
    __":
    -0.54
     ujednoznacz
    -0.53
    PerformLayout
    -0.53
    moveToFirst
    -0.53
    POSITIVE LOGITS
    uxxxx
    0.64
    rouvez
    0.54
    RTGC
    0.52
    apur
    0.51
    ніципа
    0.51
    magine
    0.48
    逅
    0.47
    setGeometry
    0.45
     mails
    0.44
     propOrder
    0.44
    Activations Density 0.303%

    No Known Activations