© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13570
    Prev
    Next
    INDEX
    Explanations

    botanical and biological scientific names, with a focus on standard abbreviations for scientists' names

    oai_token-act-pair · gemini-2.0-flash

    plant scientific names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     CreateTagHelper
    -0.83
    +#+#
    -0.82
    存于互联网档案馆
    -0.81
    RegressionTest
    -0.79
     مشين
    -0.77
    RenderAtEndOf
    -0.77
    KommentareTeilen
    -0.71
    Datuak
    -0.69
     <>",
    -0.68
     Roskov
    -0.67
    POSITIVE LOGITS
    getExternal
    0.47
     glück
    0.45
     Zappa
    0.42
    DockStyle
    0.41
     festival
    0.41
     صوتيه
    0.41
    gage
    0.39
    ochim
    0.39
    ioli
    0.38
    estival
    0.37
    Activations Density 2.331%

    No Known Activations