© 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. 10039
    Prev
    Next
    INDEX
    Explanations

    strings that begin with an equal sign and a double quote, then a backslash, then a digit

    oai_token-act-pair · gemini-2.0-flash

    LaTeX image inclusion

    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
    medriver
    -0.68
     autorytatywna
    -0.68
     createState
    -0.66
    parsedMessage
    -0.64
    ContentAsync
    -0.64
    ElementException
    -0.60
    EndGlobalSection
    -0.60
    msgSender
    -0.60
     ujednoznacz
    -0.59
    AnimationsModule
    -0.59
    POSITIVE LOGITS
    CreateModel
    0.50
    OCCURRED
    0.47
     Erişim
    0.45
     Protobuf
    0.45
     Publish
    0.45
     [*]
    0.44
    ngrx
    0.41
     apparente
    0.41
     Tages
    0.41
     Quill
    0.41
    Activations Density 0.306%

    No Known Activations