© 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. 10157
    Prev
    Next
    INDEX
    Explanations

    technical words related to physics, specifically electricity and magnetism.

    oai_token-act-pair · gemini-2.0-flash

    electricity or magnetic fields

    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
    SourceChecksum
    -0.83
    oredCriteria
    -0.78
    dafx
    -0.76
     ErrIntOverflow
    -0.75
    tagHelperRunner
    -0.74
    fjspx
    -0.74
     незавершена
    -0.71
    تقاوى
    -0.70
    AnimationsModule
    -0.68
     utafitiHapana
    -0.68
    POSITIVE LOGITS
    хозяй
    0.52
     fluxes
    0.45
     bParam
    0.43
    routing
    0.43
    ={`${
    0.42
     reactions
    0.41
    Smart
    0.40
    <bos>
    0.40
    ági
    0.40
     $("
    0.40
    Activations Density 1.050%

    No Known Activations