© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3918
    Prev
    Next
    INDEX
    Explanations

    the word "success" or the French word "réussi".

    oai_token-act-pair · gemini-2.0-flash

    success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     transfieras
    -0.67
    DotNetBar
    -0.65
    MockBean
    -0.60
    ScopeManager
    -0.56
    UnusedPrivate
    -0.54
     nahilalakip
    -0.54
    Personensuche
    -0.53
    Espèce
    -0.53
     Bourgoin
    -0.52
     artikkelen
    -0.52
    POSITIVE LOGITS
     success
    1.91
     Success
    1.82
     successful
    1.78
     SUCCESS
    1.77
    Success
    1.71
    success
    1.67
     succès
    1.57
     sucess
    1.56
    successful
    1.55
     Successful
    1.55
    Activations Density 0.375%

    No Known Activations