© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12364
    Prev
    Next
    INDEX
    Explanations

    words related to biological and chemical laboratory procedures, reagents, and equipment

    oai_token-act-pair · gemini-2.0-flash

    cell culture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    URLException
    -0.72
     viewWillAppear
    -0.62
    Osob
    -0.53
    atrième
    -0.50
     nuage
    -0.50
     perſon
    -0.50
    Подроб
    -0.49
    kac
    -0.49
    VersionUID
    -0.48
    __(/*!
    -0.47
    POSITIVE LOGITS
    scriptcase
    0.59
     Meksiku
    0.57
     дописавши
    0.55
    رشف
    0.54
    arote
    0.50
     Мексичка
    0.47
    adaptiveStyles
    0.47
    AutoField
    0.46
     autorytatywna
    0.45
     ditutup
    0.45
    Activations Density 2.239%

    No Known Activations