© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11761
    Prev
    Next
    INDEX
    Explanations

    medical terminology, especially related to children's conditions and drug interventions

    oai_token-act-pair · gemini-2.0-flash

    technical terms or code-like syntax

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

    medical conditions

    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
     newBuilder
    -0.79
    modelBuilder
    -0.64
    PerformLayout
    -0.64
     Италијани
    -0.60
     дописавши
    -0.60
    StoreMessageInfo
    -0.58
    ContextHolder
    -0.57
     JAXBElement
    -0.56
    BagConstraints
    -0.56
     IconData
    -0.56
    POSITIVE LOGITS
    posedge
    0.45
    mappedBy
    0.45
     saites
    0.45
     неба
    0.43
    وف
    0.42
    removeAttr
    0.42
    AddTagHelper
    0.42
     σύν
    0.41
    ConstraintMaker
    0.41
    thered
    0.40
    Activations Density 1.255%

    No Known Activations