© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9227
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and technical language.

    oai_token-act-pair · gemini-2.0-flash

    avoid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     EconPapers
    -0.64
    openConnection
    -0.60
     Deliber
    -0.57
    lax
    -0.56
    emptyset
    -0.54
     pardoned
    -0.54
     Jeden
    -0.54
     volu
    -0.53
    oa̍t
    -0.52
     Marlins
    -0.51
    POSITIVE LOGITS
     مرئيه
    0.46
    encanaan
    0.44
    colin
    0.43
     NSCoder
    0.43
     IconData
    0.42
    basan
    0.41
    couvrez
    0.41
     découvertes
    0.41
    городи
    0.40
     oprot
    0.40
    Activations Density 5.194%

    No Known Activations