© 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. 5265
    Prev
    Next
    INDEX
    Explanations

    references to the TV show Agents of Shield and similar media

    oai_token-act-pair · gemini-2.0-flash

    unusual or complex words

    np_token-act-pair-logits · gpt-4o-mini
    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
     dAtA
    -0.79
     lenker
    -0.73
    tagHelperRunner
    -0.73
    writeField
    -0.71
    WireFormatLite
    -0.68
    UserScript
    -0.68
    клопе
    -0.68
    ChildScrollView
    -0.65
     jsPsych
    -0.64
    styleType
    -0.61
    POSITIVE LOGITS
     obr
    0.56
    jface
    0.56
    χεία
    0.52
     établissements
    0.50
    eader
    0.48
     Público
    0.48
     impré
    0.47
     CGSize
    0.46
    InMemory
    0.45
     Angriff
    0.45
    Activations Density 0.383%

    No Known Activations