© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7921
    Prev
    Next
    INDEX
    Explanations

    the word "of", especially in longer phrases

    oai_token-act-pair · gemini-2.0-flash

    Random snippets of text

    np_max-act-logits · gemini-2.0-flash

    ▁of

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    runs
    -0.35
     formel
    -0.35
     run
    -0.35
     Runs
    -0.34
     amus
    -0.33
     stap
    -0.33
    ляє
    -0.33
     عق
    -0.33
    ob
    -0.33
    כ
    -0.32
    POSITIVE LOGITS
    IndentedString
    0.88
    InitVars
    0.83
    HostException
    0.81
    HtmlAttribute
    0.80
     الحره
    0.79
    :✨
    0.78
     CreateTagHelper
    0.77
     destiny
    0.77
    twimg
    0.76
     فريبيس
    0.76
    Activations Density 0.515%

    No Known Activations