© 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. 206
    Prev
    Next
    INDEX
    Explanations

    code snippets including Java and React code

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · 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
    MigrationBuilder
    -0.88
     esternos
    -0.86
     <<<<<<<<<<<<<<
    -0.83
    FunctionFlags
    -0.76
     препратки
    -0.74
    adaptiveStyles
    -0.72
    zbęd
    -0.70
    Personensuche
    -0.67
     transfieras
    -0.66
     pinulongan
    -0.65
    POSITIVE LOGITS
     equality
    0.51
    Equality
    0.50
    mappedBy
    0.49
     election
    0.48
     clubes
    0.46
    онер
    0.46
    📝
    0.46
    wellen
    0.46
    Election
    0.45
    folgen
    0.45
    Activations Density 0.627%

    No Known Activations