© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9486
    Prev
    Next
    INDEX
    Explanations

    the phrase "one of a kind"

    oai_token-act-pair · gemini-2.0-flash

    kind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     estimés
    -0.72
     himo
    -0.61
    KommentareTeilen
    -0.57
    InputTagHelper
    -0.56
    jdt
    -0.54
    httphttps
    -0.52
     cami
    -0.51
     écoulé
    -0.51
     CURIAM
    -0.50
     <<<<<<<<<<<<<<
    -0.50
    POSITIVE LOGITS
     unique
    0.84
     rare
    0.82
    Rare
    0.72
     Rare
    0.69
     rarity
    0.68
     uniqueness
    0.67
    unique
    0.67
    rare
    0.66
     Unique
    0.66
     extraordinary
    0.66
    Activations Density 0.696%

    No Known Activations