© 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. 12330
    Prev
    Next
    INDEX
    Explanations

    terms related to computer graphics and audio plugins

    oai_token-act-pair · gemini-2.0-flash

    game/software development

    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
    Negative Logits
     propOrder
    -0.81
    ########.
    -0.75
    出版年
    -0.73
     AssemblyProduct
    -0.71
    GraphicsUnit
    -0.68
    SharedCtor
    -0.66
    LookAnd
    -0.63
    semantics
    -0.63
    ArrowToggle
    -0.63
     HttpNotFound
    -0.63
    POSITIVE LOGITS
     jadx
    0.47
     légitime
    0.47
     loopt
    0.45
     Nationality
    0.44
     suspects
    0.44
    товано
    0.44
     nationalities
    0.43
     Ogil
    0.42
     sacré
    0.42
     reafon
    0.42
    Activations Density 2.738%

    No Known Activations