© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14157
    Prev
    Next
    INDEX
    Explanations

    mentions of either the word "cup" or references to food.

    oai_token-act-pair · gemini-2.0-flash

    cup

    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
    Negative Logits
    存于互联网档案馆
    -0.66
     الحره
    -0.58
      
    -0.57
    σκευ
    -0.56
    Conclu
    -0.55
     acá
    -0.53
     rosca
    -0.52
    homonymie
    -0.52
    livejournal
    -0.52
     povezave
    -0.51
    POSITIVE LOGITS
    })`
    0.65
     يتيمه
    0.63
    IDATE
    0.62
    ations
    0.61
    aneous
    0.61
    ]').
    0.60
    ftagPool
    0.60
    InitVars
    0.60
    titut
    0.59
    MLLoader
    0.59
    Activations Density 0.966%

    No Known Activations