© 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. 14004
    Prev
    Next
    INDEX
    Explanations

    a mix of foreign language words (especially Portuguese), chemical terms, and table formatting structures

    oai_token-act-pair · 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
    stående
    -0.58
    //
    -0.56
     pinulongan
    -0.54
    handedly
    -0.54
    
    -0.54
     Th
    -0.54
    softc
    -0.54
    }*/
    -0.53
    ,:]
    -0.52
    herself
    -0.52
    POSITIVE LOGITS
    ंदीखरीदारी
    0.62
    qrt
    0.61
     Viceroy
    0.59
    ValueGeneration
    0.57
    PhysRev
    0.56
    dziew
    0.54
    bootstrapcdn
    0.54
    ComponentScan
    0.54
    iNdEx
    0.53
    HasAnnotation
    0.52
    Activations Density 7.828%

    No Known Activations