© 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. 10901
    Prev
    Next
    INDEX
    Explanations

    code snippets, likely in a language other than English, related to the Facebook account kit

    oai_token-act-pair · gemini-2.0-flash

    an

    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
    AndEndTag
    -0.91
    protoc
    -0.66
     NSCoder
    -0.63
    AccessorTable
    -0.63
    principalTable
    -0.61
    ंदीखरीदारी
    -0.61
    XmlAccessType
    -0.61
    ainville
    -0.59
    Portail
    -0.59
    StructEnd
    -0.57
    POSITIVE LOGITS
    ViewFeatures
    0.49
    TagHelpers
    0.47
     so
    0.44
    ----</
    0.43
     se
    0.41
     Shared
    0.41
    ykjav
    0.40
    media
    0.39
    Shared
    0.38
     SOLE
    0.38
    Activations Density 1.395%

    No Known Activations