© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9916
    Prev
    Next
    INDEX
    Explanations

    syntax appearing in programming languages, mathematical equations, and tables

    oai_token-act-pair · gemini-2.0-flash

    code and tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    slidesToShow
    -0.80
    ViewFeatures
    -0.66
    lapsingToolbar
    -0.63
     JpaRepository
    -0.62
    Espèce
    -0.62
    hésite
    -0.60
     Vikipedi
    -0.60
    HostException
    -0.59
     виправивши
    -0.57
    ///</
    -0.57
    POSITIVE LOGITS
     communautaire
    0.48
     bati
    0.45
    исленность
    0.44
    elf
    0.42
    char
    0.41
     أمريكي
    0.41
     rağmen
    0.41
    Història
    0.40
    pa
    0.40
    mix
    0.39
    Activations Density 4.675%

    No Known Activations