© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9876
    Prev
    Next
    INDEX
    Explanations

    the word "trial" when discussing the context of a court case

    oai_token-act-pair · gemini-2.0-flash

    trial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     shaded
    -0.53
     trial
    -0.50
    Keep
    -0.48
     keep
    -0.48
     Trial
    -0.47
     offside
    -0.47
     Keep
    -0.47
    keep
    -0.46
    Format
    -0.45
     Bist
    -0.45
    POSITIVE LOGITS
    adpleegd
    0.91
    migrationBuilder
    0.91
     صوتيه
    0.86
     mergeFrom
    0.81
     OFDb
    0.78
    DispatchToProps
    0.77
    Atsauces
    0.74
    ]){
    0.73
    featureID
    0.73
     onPostExecute
    0.73
    Activations Density 0.160%

    No Known Activations