© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11028
    Prev
    Next
    INDEX
    Explanations

    words that researchers would use in scientific papers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    /*
    -0.61
    AccessorTable
    -0.60
    removeFrom
    -0.56
    himovic
    -0.55
    aderie
    -0.54
    /**
    -0.54
    ^(@)
    -0.52
    riceps
    -0.52
    inerary
    -0.49
    bekah
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.97
    bootstrapcdn
    0.81
     EconPapers
    0.73
     invokingState
    0.59
     الأصل
    0.57
     orice
    0.56
    SizeMode
    0.55
    ScopeManager
    0.55
    لاعب
    0.53
    NewLabel
    0.53
    Activations Density 2.098%

    No Known Activations