© 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. 13602
    Prev
    Next
    INDEX
    Explanations

    code snippets in a language that resembles javascript, especially those including the word "vez"

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    saraba
    -0.58
     طرف
    -0.51
     wholes
    -0.49
     Misch
    -0.48
    ci
    -0.47
    AccessException
    -0.46
    vode
    -0.44
    CodeAnalysis
    -0.43
    nem
    -0.42
    teni
    -0.42
    POSITIVE LOGITS
     EClass
    0.61
    WriteTagHelper
    0.60
    XmlRootElement
    0.59
     disambiguazione
    0.59
    SizeF
    0.56
    fjspx
    0.56
     yii
    0.56
    niająca
    0.55
     protoimpl
    0.54
    quiti
    0.54
    Activations Density 0.414%

    No Known Activations