© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11311
    Prev
    Next
    INDEX
    Explanations

    past-tense action related to people, particularly involving time and money.

    oai_token-act-pair · gemini-2.0-flash

    months

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ConstraintMaker
    -0.70
    kháu
    -0.66
    ParallelGroup
    -0.60
     antaranya
    -0.57
     autorytatywna
    -0.56
    boxylic
    -0.56
    TestingModule
    -0.56
     viewDidLoad
    -0.54
    tvguidetime
    -0.53
    :✨
    -0.52
    POSITIVE LOGITS
     September
    0.99
     August
    0.97
     June
    0.92
     April
    0.91
     February
    0.89
     July
    0.87
     October
    0.87
     last
    0.87
     January
    0.86
     December
    0.86
    Activations Density 2.045%

    No Known Activations