© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10919
    Prev
    Next
    INDEX
    Explanations

    words or short phrases related to math, physics, and scientific study

    oai_token-act-pair · gemini-2.0-flash

    values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    arxiv
    -0.55
    unhofer
    -0.55
    bium
    -0.54
    byshev
    -0.52
    syscall
    -0.52
     jadx
    -0.50
    igata
    -0.50
    دهی
    -0.50
    iyle
    -0.50
     η
    -0.50
    POSITIVE LOGITS
     EconPapers
    0.99
    verwijspagina
    0.79
     disambiguazione
    0.73
     DataTypes
    0.72
     ujednoznacz
    0.69
    ՚
    0.65
     esternos
    0.64
    []
    0.64
     <=",
    0.64
     nahilalakip
    0.64
    Activations Density 6.079%

    No Known Activations