© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16368
    Prev
    Next
    INDEX
    Explanations

    code snippets that define constant variables in Java

    oai_token-act-pair · gemini-2.0-flash

    final

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     lenker
    -0.58
     sia
    -0.42
     ही
    -0.42
     OTHERWISE
    -0.41
     only
    -0.41
    ंदीखरीदारी
    -0.40
     !}
    -0.40
    __))
    -0.40
     oport
    -0.39
     mata
    -0.39
    POSITIVE LOGITS
    UnusedPrivate
    0.85
     referenties
    0.77
    UrlResolution
    0.74
     pleaſure
    0.66
     Monfieur
    0.65
    BeginContext
    0.65
    posedge
    0.65
    makeConstraints
    0.65
     NTIS
    0.64
     AssemblyProduct
    0.63
    Activations Density 3.045%

    No Known Activations