© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13789
    Prev
    Next
    INDEX
    Explanations

    code snippets that use bracket notation to access array elements and/or object properties

    oai_token-act-pair · gemini-2.0-flash

    [

    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
    +#+#
    -1.09
    RegistryLite
    -1.00
    WriteBarrier
    -0.97
     JpaRepository
    -0.94
    MigrationBuilder
    -0.94
     Roskov
    -0.94
    #+#
    -0.88
     EconPapers
    -0.88
     OFDb
    -0.88
    modelBuilder
    -0.86
    POSITIVE LOGITS
     (
    0.46
    c
    0.43
     family
    0.41
     els
    0.40
    ↵
    0.39
     parent
    0.37
     Family
    0.37
    ein
    0.37
     aleg
    0.37
    min
    0.36
    Activations Density 1.187%

    No Known Activations