© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 15567
    Prev
    Next
    INDEX
    Explanations

    the word "more" and other terms/phrases implying comparisons, especially in medical, legal, or analytical contexts

    oai_token-act-pair · gemini-2.0-flash

    more

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     then
    -2.69
    then
    -2.11
    Then
    -1.94
     Then
    -1.86
     entonces
    -1.77
     então
    -1.61
     dann
    -1.59
     THEN
    -1.52
     allora
    -1.49
    THEN
    -1.38
    POSITIVE LOGITS
     disambiguazione
    0.65
    hahn
    0.59
    fromnode
    0.55
    ément
    0.54
    kloped
    0.53
    <<"\
    0.52
    elow
    0.52
    gegeven
    0.52
     <<
    0.52
    arakhand
    0.51
    Activations Density 1.150%

    No Known Activations