© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9704
    Prev
    Next
    INDEX
    Explanations

    mentions of people in some kind of relationship

    oai_token-act-pair · gemini-2.0-flash

    vice and crime

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     betweenstory
    -0.72
     للمعارف
    -0.72
    Portail
    -0.66
     CURLOPT
    -0.63
     MessageBoxIcon
    -0.63
    ChildScrollView
    -0.61
    omla
    -0.58
    BeginContext
    -0.58
     }>
    -0.58
    webElement
    -0.57
    POSITIVE LOGITS
     vice
    0.85
     Vice
    0.67
     crime
    0.65
    Vice
    0.61
    crime
    0.57
     organized
    0.55
     Crime
    0.54
    gaming
    0.54
     cờ
    0.52
     gaming
    0.51
    Activations Density 1.903%

    No Known Activations