© 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. 14457
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets, as well as abbreviated names such as "et al." and HTML markup

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     Their
    -0.80
     This
    -0.69
     They
    -0.68
     That
    -0.66
     These
    -0.64
     The
    -0.64
     It
    -0.62
     de
    -0.57
     About
    -0.57
    Their
    -0.56
    POSITIVE LOGITS
    MigrationBuilder
    0.94
    Datuak
    0.91
     secondly
    0.83
    ViewFeatures
    0.78
     purpoſe
    0.77
     Geen
    0.76
    はじめに
    0.75
    ValueStyle
    0.73
     whoſe
    0.72
     Efq
    0.72
    Activations Density 3.346%

    No Known Activations