© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1813
    Prev
    Next
    INDEX
    Explanations

    the phrase "one of the"

    oai_token-act-pair · gemini-2.0-flash

    superlative descriptors

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

    of

    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
    Negative Logits
     how
    -0.65
    how
    -0.63
     why
    -0.57
     autorytatywna
    -0.56
    why
    -0.53
    what
    -0.52
    How
    -0.51
    ایج
    -0.51
    emény
    -0.51
    delwed
    -0.50
    POSITIVE LOGITS
     toughest
    0.77
     strongest
    0.76
     best
    0.72
     fastest
    0.72
    largest
    0.71
    worst
    0.70
     finest
    0.69
    greatest
    0.69
     largest
    0.69
     worst
    0.68
    Activations Density 0.537%

    No Known Activations