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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13703
    Prev
    Next
    INDEX
    Explanations

    words related to courts and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    police

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     conviction
    -0.89
     convicted
    -0.74
     convictions
    -0.72
     trial
    -0.70
     jury
    -0.68
     condenado
    -0.66
     convict
    -0.64
     verdicts
    -0.64
     TRIAL
    -0.63
     Trial
    -0.63
    POSITIVE LOGITS
     police
    0.90
    
    0.80
    police
    0.76
    Police
    0.73
     Police
    0.72
     FontWeight
    0.65
     POLICE
    0.64
     arrested
    0.57
     arrest
    0.56
    POL
    0.56
    Activations Density 1.159%

    No Known Activations