© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2506
    Prev
    Next
    INDEX
    Explanations

    sentences relating to the immune system on a cellular level

    oai_token-act-pair · gemini-2.0-flash

    terms related to proteins and genetics

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

    proteins

    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
    migrationBuilder
    -0.74
     فريبيس
    -0.64
    Digitized
    -0.58
    GEBURTSDATUM
    -0.57
     RSSSF
    -0.56
    aculture
    -0.54
    IsContent
    -0.53
     cæ
    -0.52
     humains
    -0.51
    nestjs
    -0.50
    POSITIVE LOGITS
     proteins
    0.84
     protein
    0.81
     protéines
    0.64
    proteins
    0.63
    protein
    0.62
    Proteins
    0.62
     Proteins
    0.60
     Protein
    0.60
     proteínas
    0.59
     genes
    0.57
    Activations Density 2.857%

    No Known Activations