© 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. 10799
    Prev
    Next
    INDEX
    Explanations

    words related to political judicial systems

    oai_token-act-pair · gemini-2.0-flash

    outside/beyond

    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
    yorsunuz
    -0.47
    ViewChild
    -0.46
    baz
    -0.45
     DRAWINGS
    -0.43
    Eloquent
    -0.43
    hados
    -0.43
     préférences
    -0.43
     lourdes
    -0.42
    AnimationsModule
    -0.42
     BaseActivity
    -0.41
    POSITIVE LOGITS
     beyond
    1.01
     outside
    0.96
    outside
    0.91
    beyond
    0.90
     above
    0.83
     Outside
    0.82
    above
    0.81
    Outside
    0.81
     immune
    0.74
     Beyond
    0.73
    Activations Density 2.807%

    No Known Activations