© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1780
    Prev
    Next
    INDEX
    Explanations

    code, numbers, and unusual names in what looks like html or LaTeX mark up

    oai_token-act-pair · gemini-2.0-flash

    proper nouns or names

    np_token-act-pair-logits · gpt-4o-mini

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     EconPapers
    -0.73
    expandindo
    -0.69
    IntoConstraints
    -0.69
    '},
    -0.64
    ])):
    -0.63
    はじめに
    -0.61
     disambiguazione
    -0.61
     AssemblyCompany
    -0.61
    principalTable
    -0.59
    PerformLayout
    -0.58
    POSITIVE LOGITS
    TestBed
    0.45
    Géographie
    0.44
    cej
    0.42
    ian
    0.42
    elemField
    0.41
     sounded
    0.40
     Extragalactic
    0.40
     thạch
    0.40
    Stat
    0.39
     yana
    0.39
    Activations Density 0.547%

    No Known Activations