© 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. 9739
    Prev
    Next
    INDEX
    Explanations

    legal or financial language related to evaluating fairness

    oai_token-act-pair · gemini-2.0-flash

    "favor" and "prefer"

    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
     favoured
    -1.76
     favour
    -1.76
     favours
    -1.68
     favor
    -1.64
     Favor
    -1.62
     favored
    -1.61
     favoring
    -1.58
     favors
    -1.55
     Fav
    -1.53
     FAVOR
    -1.52
    POSITIVE LOGITS
     Pre
    0.64
     pre
    0.61
    Pre
    0.61
    pre
    0.58
     P
    0.56
     F
    0.53
     f
    0.50
    F
    0.48
     प
    0.48
    f
    0.47
    Activations Density 1.146%

    No Known Activations