© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10004
    Prev
    Next
    INDEX
    Explanations

    mentions of taking advantage of something or advantageous situations

    oai_token-act-pair · gemini-2.0-flash

    advantage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    定的
    -0.44
    kies
    -0.43
    setGravity
    -0.43
    indicated
    -0.43
    Referencies
    -0.43
    \&
    -0.42
     ocorrer
    -0.42
     palabra
    -0.42
    Kontrola
    -0.41
     kie
    -0.41
    POSITIVE LOGITS
     AssemblyCulture
    0.80
    ſelf
    0.77
     Majefty
    0.75
    存于互联网档案馆
    0.74
     raiſ
    0.72
     Italijanski
    0.71
     myſelf
    0.68
     uſe
    0.68
     disambiguazione
    0.68
     propOrder
    0.67
    Activations Density 1.184%

    No Known Activations