© 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. 4831
    Prev
    Next
    INDEX
    Explanations

    violent, unequal, abusive interactions between people

    oai_token-act-pair · gemini-2.0-flash

    Abuse and punishment

    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
    BeginContext
    -0.78
     warrant
    -0.77
    AddTagHelper
    -0.75
     warrants
    -0.74
    TagMode
    -0.73
    
    -0.71
     المعيارى
    -0.69
    UnusedPrivate
    -0.69
     continúas
    -0.68
     урна
    -0.68
    POSITIVE LOGITS
    Beat
    0.58
     Beat
    0.53
     sma
    0.53
     beat
    0.52
     beating
    0.50
     sp
    0.46
    ashian
    0.46
     smack
    0.45
    beat
    0.45
    beaten
    0.45
    Activations Density 0.512%

    No Known Activations