© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1925
    Prev
    Next
    INDEX
    Explanations

    instances where someone is apologizing or asking for an exception

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     SwiftUI
    -0.62
    Datuak
    -0.60
    writeField
    -0.60
    contentLoaded
    -0.56
     clumsy
    -0.55
     chaotic
    -0.53
     unreasonably
    -0.53
     gratuitous
    -0.52
     ridiculous
    -0.52
     poor
    -0.51
    POSITIVE LOGITS
    وردار
    0.68
    ViewFeatures
    0.54
    aziland
    0.54
    cèse
    0.51
    adpleegd
    0.51
    पया
    0.50
     Auff
    0.50
     opérés
    0.49
     otomatig
    0.49
     vif
    0.48
    Activations Density 8.508%

    No Known Activations