© 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. 13995
    Prev
    Next
    INDEX
    Explanations

    words used in software testing code

    oai_token-act-pair · gemini-2.0-flash

    Test

    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
    Negative Logits
     Monfieur
    -1.67
     Theſe
    -1.54
     photolibrary
    -1.48
     doubtnut
    -1.48
     uſed
    -1.45
     myſelf
    -1.42
     ་་
    -1.41
     Jefus
    -1.41
     Efq
    -1.41
    ſelf
    -1.38
    POSITIVE LOGITS
     I
    0.77
     "
    0.75
     C
    0.74
     _
    0.73
     D
    0.72
     M
    0.71
     It
    0.70
     V
    0.69
     Me
    0.69
     Per
    0.69
    Activations Density 1.657%

    No Known Activations