© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6125
    Prev
    Next
    INDEX
    Explanations

    technical jargon, especially related to biology and business innovation

    oai_token-act-pair · 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
     Monfieur
    -0.80
     myſelf
    -0.71
     Jefus
    -0.68
     purpoſe
    -0.67
     Majefty
    -0.65
     mourir
    -0.63
     himſelf
    -0.63
     externi
    -0.62
     themſelves
    -0.62
     Efq
    -0.60
    POSITIVE LOGITS
    addCriterion
    0.69
     المعيارى
    0.66
     imageNamed
    0.63
    الإنجليزية
    0.61
    PullParser
    0.60
     Superhosts
    0.60
    XmlAccessorType
    0.59
    fromnode
    0.57
    ArrowToggle
    0.55
    exitRule
    0.54
    Activations Density 1.236%

    No Known Activations