© 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. 12534
    Prev
    Next
    INDEX
    Explanations

    technical language for science and engineering, including medicine, computers, and botany

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical processes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.73
    }),
    -0.71
    findpost
    -0.70
     ویکی‌پدیا
    -0.69
    GEBURTSDATUM
    -0.69
    timewa
    -0.67
     Numerade
    -0.67
    Personensuche
    -0.66
    ftagPool
    -0.65
     AssemblyProduct
    -0.65
    POSITIVE LOGITS
    ViewImports
    0.53
     strtotime
    0.49
    ynı
    0.45
    strtotime
    0.44
    ,
    0.41
    EDEFAULT
    0.40
     onAnimation
    0.38
     instead
    0.38
     raccolta
    0.38
     enthalpy
    0.37
    Activations Density 5.768%

    No Known Activations