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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6259
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to policing, arrests, and criminal activity

    oai_token-act-pair · gemini-2.0-flash

    Arrests and legal proceedings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     arrest
    -1.16
     arrests
    -0.98
    Arrest
    -0.96
     Arrest
    -0.93
     arrested
    -0.91
     detained
    -0.85
    arrest
    -0.81
     detention
    -0.81
     arresting
    -0.80
     Catch
    -0.76
    POSITIVE LOGITS
     AR
    0.73
    ar
    0.71
    AR
    0.69
     ar
    0.69
    ScopeManager
    0.64
     فريبيس
    0.63
     Ar
    0.58
    Personensuche
    0.57
    Ar
    0.57
     MainAxisSize
    0.56
    Activations Density 6.578%

    No Known Activations