© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15808
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent crime and incarceration

    oai_token-act-pair · gemini-2.0-flash

    violence

    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
    rungsseite
    -0.51
    ziehung
    -0.48
     &___
    -0.42
     cani
    -0.39
     unità
    -0.38
     امريكا
    -0.37
     units
    -0.37
    pres
    -0.37
    รม
    -0.37
     falta
    -0.36
    POSITIVE LOGITS
    basicConfig
    0.89
     للمعارف
    0.79
     surla
    0.74
     transférez
    0.73
    principalColumn
    0.73
    erover
    0.71
     تضيفلها
    0.71
    =$?
    0.69
    Enllaces
    0.68
    مصادر
    0.65
    Activations Density 1.312%

    No Known Activations