© 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. 9430
    Prev
    Next
    INDEX
    Explanations

    the words "prove", "once", and "approach"

    oai_token-act-pair · gemini-2.0-flash

    prove

    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
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -1.17
     a
    -1.09
     all
    -0.94
     in
    -0.93
     non
    -0.91
     some
    -0.87
     an
    -0.86
     local
    -0.82
     most
    -0.79
     multiple
    -0.78
    POSITIVE LOGITS
     auroit
    1.17
     feroit
    1.17
     réfugi
    1.16
     étoit
    1.15
     ainfi
    1.14
     étoient
    1.14
     avoient
    1.13
     AppColors
    1.09
     pouvoit
    1.08
     mourut
    1.06
    Activations Density 1.760%

    No Known Activations