© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2104
    Prev
    Next
    INDEX
    Explanations

    words related to science like physics, math, medicine and also related to foreign languages (unicode).

    oai_token-act-pair · gemini-2.0-flash

    Research abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     abstract
    -0.79
     Abstract
    -0.75
    Abstract
    -0.71
     abstrato
    -0.65
    .*")]
    -0.62
     resourceCulture
    -0.59
     abstracts
    -0.59
     ABSTRACT
    -0.58
    abstract
    -0.58
    Medien
    -0.58
    POSITIVE LOGITS
    цездатний
    0.63
    adaptiveStyles
    0.58
     AssemblyTitle
    0.56
     utafitiHapana
    0.56
    }{*}{
    0.55
     وتسجيلات
    0.54
     transfieras
    0.52
    ıca
    0.49
    Parcelize
    0.49
    AccessorTable
    0.47
    Activations Density 13.230%

    No Known Activations