© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 234
    Prev
    Next
    INDEX
    Explanations

    references to figures, sections, tables, and numbered items, often using letters and numbers

    oai_token-act-pair · gemini-2.0-flash

    h

    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
    Negative Logits
     disponibilités
    -0.54
    óbal
    -0.50
    Peb
    -0.47
    aimerais
    -0.46
     cả
    -0.45
     Pud
    -0.45
    rolid
    -0.45
     compren
    -0.44
     Poi
    -0.44
     Liber
    -0.44
    POSITIVE LOGITS
     >=",
    0.85
     eighth
    0.83
    8
    0.79
    ⁸
    0.78
    rungsseite
    0.77
     ویکی‌پدیا
    0.77
     CreateTagHelper
    0.76
     octavo
    0.73
     estekak
    0.71
    HostException
    0.70
    Activations Density 3.953%

    No Known Activations