© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11420
    Prev
    Next
    INDEX
    Explanations

    statistically significant differences in legal and medical outcomes based on race.

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     myſelf
    -2.03
     Monfieur
    -1.98
     raiſ
    -1.98
     itſelf
    -1.98
     Theſe
    -1.95
     Efq
    -1.93
     Reſ
    -1.84
     ſche
    -1.80
     faſt
    -1.80
     pleaſure
    -1.80
    POSITIVE LOGITS
     
    0.96
      
    0.85
    ,
    0.81
    ↵
    0.79
     (
    0.77
    <eos>
    0.76
     I
    0.74
     the
    0.73
     of
    0.70
    ↵↵
    0.70
    Activations Density 3.985%

    No Known Activations