© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10709
    Prev
    Next
    INDEX
    Explanations

    abbreviations and short words, especially those beginning with "sc" and including the word "auto"

    oai_token-act-pair · gemini-2.0-flash

    sc

    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
    EDEFAULT
    -0.90
     MainAxisSize
    -0.90
    crapers
    -0.88
     nahilalakip
    -0.81
     CreateTagHelper
    -0.81
     disambiguazione
    -0.81
    tagHelperRunner
    -0.78
     StatefulWidget
    -0.77
     BoxFit
    -0.75
    djangoproject
    -0.74
    POSITIVE LOGITS
     enfans
    1.16
     avoient
    0.95
     feroit
    0.95
     étoient
    0.94
     ainfi
    0.91
     étoit
    0.91
     debout
    0.87
     ſtate
    0.87
     auroit
    0.86
     Majefty
    0.84
    Activations Density 1.215%

    No Known Activations