© 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. 2983
    Prev
    Next
    INDEX
    Explanations

    the word 'rapid', and also to a lesser degree words related to wholeness

    oai_token-act-pair · gemini-2.0-flash

    rapid

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    AddTagHelper
    -0.85
    er
    -0.85
    ########.
    -0.83
     للمعارف
    -0.83
     disambiguazione
    -0.81
    Tikang
    -0.77
    
    -0.74
    :✨
    -0.68
     CanadaChoose
    -0.67
     /\.(
    -0.66
    POSITIVE LOGITS
    }}">
    0.58
     giao
    0.58
     bune
    0.55
    auge
    0.55
    ओं
    0.52
     bună
    0.51
    arele
    0.50
     Bege
    0.50
    asikan
    0.49
    fulness
    0.48
    Activations Density 0.713%

    No Known Activations