© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3849
    Prev
    Next
    INDEX
    Explanations

    code or code-like syntax and mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ^(@)
    -0.56
    })->
    -0.55
     satisfe
    -0.55
     مشين
    -0.54
     nemlig
    -0.53
    wiſe
    -0.52
     enfans
    -0.50
    \{\\
    -0.50
     dite
    -0.49
     campamento
    -0.48
    POSITIVE LOGITS
    LookAnd
    0.96
    ValueStyle
    0.85
    RegistryLite
    0.70
    ItemBackground
    0.69
     AssemblyCulture
    0.65
    __(/*!
    0.64
    Portale
    0.63
     knex
    0.62
    ThroughAttribute
    0.59
     AssemblyProduct
    0.59
    Activations Density 1.231%

    No Known Activations