© 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. 10756
    Prev
    Next
    INDEX
    Explanations

    complex biological terms related to cell structure and function

    oai_token-act-pair · gemini-2.0-flash

    gene expression terminology

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

    Cell biology research

    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
     RSSSF
    -0.71
     judiciaire
    -0.65
    setVerticalGroup
    -0.64
     disponibilités
    -0.63
    Lycka
    -0.63
     Enquiries
    -0.63
     Catawiki
    -0.61
     NDEBUG
    -0.60
    ItemBackground
    -0.59
    calaure
    -0.59
    POSITIVE LOGITS
    EndContext
    0.47
    MigrationBuilder
    0.44
    Gön
    0.43
     G
    0.42
    ën
    0.41
     popol
    0.41
     Spire
    0.41
     F
    0.40
     doc
    0.40
    ppus
    0.39
    Activations Density 3.127%

    No Known Activations