© 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. 3329
    Prev
    Next
    INDEX
    Explanations

    the word "lift"

    oai_token-act-pair · gemini-2.0-flash

    lift

    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
     Audiodateien
    -0.99
     تضيفلها
    -0.84
    存于互联网档案馆
    -0.81
     ویکی‌پدیا
    -0.81
    LayoutStyle
    -0.78
     nonatomic
    -0.71
    âng
    -0.70
    uxxxx
    -0.69
    multicolumn
    -0.68
     defaultstate
    -0.68
    POSITIVE LOGITS
     offerts
    0.66
     extérieurs
    0.65
     juridiques
    0.65
     industriels
    0.62
     fermés
    0.61
     pauvres
    0.61
     parlent
    0.61
     américains
    0.60
     ouvriers
    0.59
     sanitaires
    0.59
    Activations Density 1.548%

    No Known Activations