© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7016
    Prev
    Next
    INDEX
    Explanations

    words relating to judgement, official condemnation in the judicial system

    oai_token-act-pair · gemini-2.0-flash

    scolding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    İstinadlar
    -0.56
     referenties
    -0.54
    beginTransaction
    -0.51
     utafitiHapana
    -0.46
    QObject
    -0.46
    ISupport
    -0.45
     szen
    -0.45
    ^{-}\
    -0.45
    ExtendWith
    -0.45
     StatefulWidget
    -0.44
    POSITIVE LOGITS
     scold
    1.02
     warning
    1.00
     scolded
    0.98
     admon
    0.97
     admonition
    0.94
     rebuke
    0.94
     rebu
    0.93
    IntoConstraints
    0.91
     warnings
    0.90
     reminding
    0.86
    Activations Density 0.786%

    No Known Activations