© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16163
    Prev
    Next
    INDEX
    Explanations

    code snippets related to MongoDB queries, especially those involving date manipulations and the 'created' field

    oai_token-act-pair · gemini-2.0-flash

    Database queries creation dates

    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
     BoxFit
    -0.66
    webElementXpaths
    -0.60
     oprot
    -0.59
    CloseOperation
    -0.58
    estyles
    -0.58
    uação
    -0.52
    StoreMessageInfo
    -0.52
     виправивши
    -0.51
    Hauptartikel
    -0.50
    లాలు
    -0.50
    POSITIVE LOGITS
    contentLoaded
    0.63
    {?>
    0.51
     ͡
    0.49
     GIPHY
    0.49
    ITURE
    0.49
     raiſ
    0.49
     snippetHide
    0.48
     Majefty
    0.48
    AnimationsModule
    0.48
     houſe
    0.48
    Activations Density 3.762%

    No Known Activations