© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10060
    Prev
    Next
    INDEX
    Explanations

    language about how to fix and build backup power systems for nuclear reactors

    oai_token-act-pair · gemini-2.0-flash

    nuclear energy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    enumi
    -0.65
     للمعارف
    -0.55
    TagMode
    -0.55
    Билгалдахарш
    -0.55
     scolas
    -0.54
    thâu
    -0.54
     giác
    -0.52
    enumii
    -0.51
    AndEndTag
    -0.51
    +#+#
    -0.51
    POSITIVE LOGITS
    titleMargin
    0.60
     propOrder
    0.60
     оригіналу
    0.54
     fVar
    0.49
     Ring
    0.47
    khar
    0.47
     Pleasure
    0.46
     Mile
    0.46
    号線
    0.46
    MockMvc
    0.45
    Activations Density 4.376%

    No Known Activations