© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13266
    Prev
    Next
    INDEX
    Explanations

    terms related to time periods, high profile and the Marvel Comic character Black Widow

    oai_token-act-pair · gemini-2.0-flash

    people and their attributes

    np_max-act · gemini-2.0-flash

    say "capitalized" Method used: 2 — tokens after are capitalized; say "capitalized"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     orologio
    -0.61
     сър
    -0.56
     ferons
    -0.54
     tratti
    -0.52
     giudi
    -0.51
     gefallen
    -0.51
     sguardo
    -0.51
     segni
    -0.50
     cucchia
    -0.50
     rilass
    -0.49
    POSITIVE LOGITS
    Попис
    1.01
     HasFactory
    0.90
    RenderAtEndOf
    0.87
    脚注の使い方
    0.85
    parsedMessage
    0.83
    expandindo
    0.81
     دیکھیے
    0.80
    TagHelper
    0.79
     समीक्षक
    0.79
    ViewFeatures
    0.78
    Activations Density 1.195%

    No Known Activations