© 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. 4431
    Prev
    Next
    INDEX
    Explanations

    parts of JSON-like metadata and documentation structures

    oai_token-act-pair · gemini-2.0-flash

    punctuation and brackets

    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
    ConstraintMaker
    -0.75
     invece
    -0.66
     disambiguazione
    -0.63
    Autoritní
    -0.59
     volon
    -0.58
     Católica
    -0.56
    __(/*!
    -0.56
    SBATCH
    -0.55
     élas
    -0.55
     Hän
    -0.55
    POSITIVE LOGITS
    OrWhiteSpace
    0.69
     يتيمه
    0.69
     wireType
    0.65
     clearColor
    0.62
    Demografia
    0.56
     null
    0.54
    =="")
    0.54
    !="")
    0.52
    migiano
    0.52
    IsNullOrEmpty
    0.52
    Activations Density 2.376%

    No Known Activations