© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10454
    Prev
    Next
    INDEX
    Explanations

    words and phrases about injustice, law and diversity

    oai_token-act-pair · gemini-2.0-flash

    Racial issues

    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
    DebuggerNonUser
    -0.66
     بيها
    -0.63
    featureID
    -0.60
    fjspx
    -0.58
    complexContent
    -0.57
    DockStyle
    -0.57
     تضيفلها
    -0.56
    sizeCache
    -0.54
    styleUrls
    -0.53
     AssemblyVersion
    -0.53
    POSITIVE LOGITS
     racial
    1.49
     racism
    1.38
     racist
    1.36
     racially
    1.31
     Racial
    1.30
     discrimination
    1.27
     diversity
    1.23
    Rac
    1.23
    racial
    1.22
     Diversity
    1.21
    Activations Density 5.707%

    No Known Activations