© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7761
    Prev
    Next
    INDEX
    Explanations

    mentions of vitamins and minerals, especially vitamin E

    oai_token-act-pair · gemini-2.0-flash

    E

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     disponibilités
    -0.77
    ########.
    -0.73
    Autoritní
    -0.70
    futbolista
    -0.61
     myſelf
    -0.59
    rawDesc
    -0.57
     оригіналу
    -0.57
    Bibliograf
    -0.57
    
    -0.55
    estive
    -0.55
    POSITIVE LOGITS
    EDEFAULT
    0.58
    XmlRootElement
    0.55
     Gideon
    0.54
    Története
    0.53
     ]}
    0.52
    Filmografie
    0.52
     Santé
    0.50
     testSet
    0.50
    InstanceState
    0.49
    각주
    0.49
    Activations Density 0.252%

    No Known Activations