© 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. 9392
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies and data collection

    oai_token-act-pair · gemini-2.0-flash

    obtained

    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
     obtained
    -1.95
     Obtained
    -1.67
    obtained
    -1.66
     obtain
    -1.63
     obtaining
    -1.53
     obtains
    -1.49
    <bos>
    -1.39
     Obtaining
    -1.38
    obtain
    -1.37
     Obtain
    -1.35
    POSITIVE LOGITS
     NUnit
    0.68
     Terr
    0.67
     EconPapers
    0.64
    InputTagHelper
    0.61
     transfieras
    0.59
    TestingModule
    0.56
    orum
    0.56
     Tear
    0.56
     setCode
    0.56
     Undo
    0.55
    Activations Density 19.122%

    No Known Activations