© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11911
    Prev
    Next
    INDEX
    Explanations

    instances of someone wondering something

    oai_token-act-pair · gemini-2.0-flash

    questions and expressions of curiosity

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

    wonder

    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
     Think
    -0.57
     termine
    -0.52
    dai
    -0.51
    dela
    -0.50
    tel
    -0.50
    Think
    -0.50
    holds
    -0.49
     Thinking
    -0.49
    retain
    -0.48
    liko
    -0.48
    POSITIVE LOGITS
     how
    0.80
    tagHelperRunner
    0.80
    AndEndTag
    0.70
     hvordan
    0.68
    exitRule
    0.68
     why
    0.68
    IsContent
    0.63
    BeginInit
    0.62
     cómo
    0.62
    how
    0.61
    Activations Density 1.309%

    No Known Activations