© 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. 14902
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to customer service and satisfaction

    oai_token-act-pair · gemini-2.0-flash

    positive experiences and helping

    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
    AddTagHelper
    -0.91
    findpost
    -0.88
     ་་
    -0.87
     ―――――
    -0.85
     crdi
    -0.82
     vectorstock
    -0.81
     MainAxisSize
    -0.81
     photolibrary
    -0.79
     itſelf
    -0.79
     ſind
    -0.77
    POSITIVE LOGITS
     he
    0.58
     up
    0.56
     his
    0.50
     lép
    0.49
     ref
    0.48
     my
    0.47
     o
    0.47
     ex
    0.46
    reda
    0.46
     over
    0.45
    Activations Density 6.936%

    No Known Activations