© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9501
    Prev
    Next
    INDEX
    Explanations

    mentions of money and winning the lottery.

    oai_token-act-pair · gemini-2.0-flash

    lottery winnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Vidite
    -0.71
    oa̍t
    -0.70
     transfieras
    -0.64
    +#+
    -0.60
     autorytatywna
    -0.59
    кипе
    -0.59
     समीक्षाओं
    -0.58
     wireType
    -0.57
    Jegyzetek
    -0.57
    ualitas
    -0.56
    POSITIVE LOGITS
     lottery
    0.71
     Lottery
    0.64
     lotto
    0.59
     Lotto
    0.57
    المناصب
    0.47
    Lotto
    0.46
    mbolos
    0.46
     jackpot
    0.42
    Lottery
    0.40
     raffle
    0.40
    Activations Density 0.045%

    No Known Activations