© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8007
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings, especially those spoken by lawyers in court

    oai_token-act-pair · gemini-2.0-flash

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    contentLoaded
    -0.75
     ſch
    -0.72
    InputBorder
    -0.71
     raiſ
    -0.71
     myſelf
    -0.70
    WriteBarrier
    -0.68
     themſelves
    -0.66
     ſche
    -0.65
     Diſ
    -0.65
    RegressionTest
    -0.65
    POSITIVE LOGITS
    unknownFields
    0.47
     invokingState
    0.40
    ंदीखरीदारी
    0.40
     commenti
    0.40
     BoxFit
    0.40
    tadır
    0.39
    èo
    0.38
    casila
    0.38
    afficheront
    0.38
    DaoImpl
    0.38
    Activations Density 0.857%

    No Known Activations