© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10734
    Prev
    Next
    INDEX
    Explanations

    technical language from scientific publications, especially in biology and chemistry

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon related to biology or chemistry

    np_token-act-pair-logits · gpt-4o-mini

    Technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     himſelf
    -0.65
     anſ
    -0.63
     auffi
    -0.63
     themſelves
    -0.61
     alamu
    -0.57
     raiſ
    -0.57
     ſet
    -0.57
     juſ
    -0.57
     purpoſe
    -0.56
     diſt
    -0.55
    POSITIVE LOGITS
    stdc
    0.63
    DockStyle
    0.60
    BagLayout
    0.60
    Tembelea
    0.59
    AutoField
    0.58
    readFileSync
    0.57
     saites
    0.57
    oredCriteria
    0.55
     jScrollPane
    0.55
     Wicidata
    0.55
    Activations Density 2.451%

    No Known Activations