© 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. 4318
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to oppression, enslavement, and technical exams

    oai_token-act-pair · gemini-2.0-flash

    slavery, cars, love, exams

    np_max-act · gemini-2.0-flash

    say "word continuation"

    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_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
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.73
    +#+#
    -0.64
    +#+
    -0.58
    verwijspagina
    -0.57
     initComponents
    -0.53
    Datuak
    -0.52
    FormTagHelper
    -0.52
    redo
    -0.51
    SpringBootTest
    -0.48
     CART
    -0.48
    POSITIVE LOGITS
    évaluateur
    0.77
    RegressionTest
    0.74
    ihnachten
    0.62
     الرياضيه
    0.60
    WireFormatLite
    0.59
    HasForeignKey
    0.59
    AnchorStyles
    0.58
    (()=>
    0.57
     nawr
    0.56
    ihnachts
    0.55
    Activations Density 1.749%

    No Known Activations