© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6982
    Prev
    Next
    INDEX
    Explanations

    text related to winning the lottery

    oai_token-act-pair · gemini-2.0-flash

    lottery

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ContentValues
    -0.70
    tagHelperRunner
    -0.69
    versiti
    -0.58
    elemField
    -0.56
    webElementXpaths
    -0.56
     inflater
    -0.55
     Lyft
    -0.54
     Roundtable
    -0.54
     decoy
    -0.53
     sienta
    -0.53
    POSITIVE LOGITS
     lot
    1.11
     Lot
    0.88
    Lot
    0.83
     LOT
    0.78
    lot
    0.77
     Power
    0.76
    LOT
    0.73
    Power
    0.67
     drawn
    0.65
     ticket
    0.63
    Activations Density 0.795%

    No Known Activations