© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings, past tense verbs, and criminal activity

    oai_token-act-pair · gemini-2.0-flash

    Legal pleadings/admissions

    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
    currentItem
    -0.54
    inerja
    -0.53
    contentLoaded
    -0.53
    foundland
    -0.52
     Southwark
    -0.51
    brü
    -0.50
    gamesh
    -0.49
     weaken
    -0.48
    nung
    -0.48
    fras
    -0.48
    POSITIVE LOGITS
    PMailer
    0.69
    formik
    0.68
    PhysRev
    0.66
     كومونز
    0.63
    eqn
    0.63
    setViewportView
    0.61
    CppMethod
    0.59
     unknownFields
    0.58
    Autoritní
    0.58
     BoxDecoration
    0.58
    Activations Density 2.541%

    No Known Activations