© 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. 5080
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with viral infection and immune response

    oai_token-act-pair · gemini-2.0-flash

    words related to data or file operations

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

    viruses

    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
     >=",
    -0.81
    expandindo
    -0.77
    SourceChecksum
    -0.69
    RetentionPolicy
    -0.66
    +#+#
    -0.65
    TagMode
    -0.59
     invokingState
    -0.59
    GeneratedMessage
    -0.59
     WaitForSeconds
    -0.57
     '\\;'
    -0.56
    POSITIVE LOGITS
    下载附件
    0.51
    findpost
    0.47
     INSEE
    0.44
    Load
    0.44
     remplacé
    0.44
     Chwiliwch
    0.43
     ControllerBase
    0.43
     load
    0.43
     papà
    0.43
    NewUrlParser
    0.43
    Activations Density 2.522%

    No Known Activations