© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10281
    Prev
    Next
    INDEX
    Explanations

    the phrase "there are" followed by some other quantity

    oai_token-act-pair · gemini-2.0-flash

    are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     vœux
    -0.61
    PositiveButton
    -0.53
     apporté
    -0.51
    all
    -0.49
    ualmente
    -0.47
     enfans
    -0.47
     astuces
    -0.47
     confronti
    -0.46
    BrowserModule
    -0.45
     faudrait
    -0.45
    POSITIVE LOGITS
     a
    0.72
     CreateTagHelper
    0.60
     AssemblyCulture
    0.57
    ưu
    0.56
     going
    0.55
     loopholes
    0.54
    esModule
    0.54
     amounts
    0.52
    Portale
    0.52
     manuscripts
    0.52
    Activations Density 3.723%

    No Known Activations