© 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. 9123
    Prev
    Next
    INDEX
    Explanations

    jargon related to blood transfusions and transplant incompatibility

    oai_token-act-pair · gemini-2.0-flash

    technical terms or fragments from code or programming

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

    medical transplants

    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
     finais
    -0.45
    cela
    -0.41
    cab
    -0.41
    {
    -0.41
     Audiodateien
    -0.41
    DataMember
    -0.40
     prevails
    -0.40
    brio
    -0.40
    Datuak
    -0.39
    bindParam
    -0.39
    POSITIVE LOGITS
    RenderAtEndOf
    0.70
     '\\;'
    0.68
    webElement
    0.68
     مرئيه
    0.66
     Chwiliwch
    0.62
    phosa
    0.59
    apura
    0.58
     Roskov
    0.57
    IBarButtonItem
    0.57
    Hozzáférés
    0.57
    Activations Density 3.004%

    No Known Activations