© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3219
    Prev
    Next
    INDEX
    Explanations

    the word "acts" in legal or scientific contexts

    oai_token-act-pair · gemini-2.0-flash

    acts

    np_max-act · gemini-2.0-flash

    ▁acts

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    AccessorTable
    -1.71
    AndEndTag
    -1.56
    AddTagHelper
    -1.49
    tagHelperRunner
    -1.45
     saites
    -1.42
     initComponents
    -1.39
     '\\;'
    -1.39
     autorytatywna
    -1.39
    EDEFAULT
    -1.39
     nahilalakip
    -1.37
    POSITIVE LOGITS
    a
    0.97
     
    0.87
    i
    0.85
    o
    0.82
    e
    0.80
    li
    0.74
    ter
    0.71
    It
    0.69
    n
    0.69
    1
    0.69
    Activations Density 2.638%

    No Known Activations