© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9979
    Prev
    Next
    INDEX
    Explanations

    instances of people planning to purchase the products they need

    oai_token-act-pair · gemini-2.0-flash

    specific terms or patterns related to shopping or product information

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    tagHelperRunner
    -0.76
    الحياه
    -0.68
     الرياضيه
    -0.63
    Abitanti
    -0.57
     समीक्षाएं
    -0.56
     engraçado
    -0.56
    InputTagHelper
    -0.55
    ModelAdmin
    -0.52
    PostBack
    -0.52
    adpleegd
    -0.51
    POSITIVE LOGITS
    #
    0.65
    opley
    0.48
     get
    0.47
     sub
    0.47
    multicolumn
    0.47
     sous
    0.47
     محفوظة
    0.47
     Get
    0.46
    ورات
    0.46
    XtraReports
    0.45
    Activations Density 0.962%

    No Known Activations