© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11445
    Prev
    Next
    INDEX
    Explanations

    words related to weddings, marriage, anniversaries, and other significant life events

    oai_token-act-pair · gemini-2.0-flash

    wedding-related terms

    np_token-act-pair-logits · gpt-4o-mini

    wedding

    np_max-act-logits · gemini-2.0-flash
    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
    sizeCache
    -0.55
     matrimonio
    -0.52
     allAfrica
    -0.51
    married
    -0.50
    ھر
    -0.50
     matrimon
    -0.50
     Marriage
    -0.50
    DebuggerNonUser
    -0.48
    Rohy
    -0.48
    Marriage
    -0.48
    POSITIVE LOGITS
     aDecoder
    0.54
     Paglinawan
    0.53
    basicConfig
    0.52
    jspx
    0.52
    "]}
    0.51
    AddTagHelper
    0.50
    itieren
    0.50
    webElement
    0.50
     Diſ
    0.50
    ContentLoaded
    0.50
    Activations Density 1.539%

    No Known Activations