© 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. 9963
    Prev
    Next
    INDEX
    Explanations

    the prefix "e-" followed by a hyphen, often related to e-commerce

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    Clik
    -0.68
    awaiter
    -0.50
     ?";
    -0.49
    scalatest
    -0.49
    rrggbb
    -0.48
    ViewChild
    -0.47
     épaules
    -0.47
    באנגלית
    -0.46
     Widodo
    -0.46
     upper
    -0.45
    POSITIVE LOGITS
    хьтан
    0.65
     autorytatywna
    0.62
     Italijanski
    0.58
    Попис
    0.58
    eroy
    0.57
    Derbyniad
    0.57
    alnız
    0.56
    MergeFrom
    0.55
    出版年
    0.54
     esternos
    0.54
    Activations Density 0.317%

    No Known Activations