© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10322
    Prev
    Next
    INDEX
    Explanations

    government or legal institutions, acts and edicts related to terrorism and law

    oai_token-act-pair · gemini-2.0-flash

    Legal Acts and Regulations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     pleaſure
    -0.77
     ſtate
    -0.74
     quæ
    -0.72
    Rüyada
    -0.70
    таратура
    -0.67
    المشاركات
    -0.66
    IsContent
    -0.65
     purpoſe
    -0.62
     ſche
    -0.62
    ########.
    -0.62
    POSITIVE LOGITS
    TRACT
    0.49
    yyj
    0.48
     članak
    0.48
    awtextra
    0.47
     Walk
    0.46
    viewDidLoad
    0.46
    InitStruct
    0.45
    licó
    0.45
     Cla
    0.44
    opy
    0.44
    Activations Density 0.580%

    No Known Activations