© 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. 13457
    Prev
    Next
    INDEX
    Explanations

    Russian and German text

    oai_token-act-pair · gemini-2.0-flash

    code/UI and other languages

    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
     négociations
    -0.62
     marquées
    -0.59
     Theſe
    -0.57
     églises
    -0.55
     renseignements
    -0.53
    những
    -0.52
    原始内容存档于
    -0.51
     cérami
    -0.50
    setScene
    -0.50
     продукции
    -0.50
    POSITIVE LOGITS
    tellers
    0.57
    routeProvider
    0.56
    httphttps
    0.53
    ftagPool
    0.53
     periods
    0.51
    pters
    0.51
    >{@
    0.49
    complexContent
    0.49
    PyExc
    0.48
     seasons
    0.47
    Activations Density 0.432%

    No Known Activations