© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12482
    Prev
    Next
    INDEX
    Explanations

    code-like tokens.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     فريبيس
    -0.79
    AndEndTag
    -0.56
    PORTE
    -0.55
    Geplaatst
    -0.54
     חיצוניים
    -0.49
    gebob
    -0.49
     Hahn
    -0.48
     nahilalakip
    -0.47
    вець
    -0.46
    b
    -0.46
    POSITIVE LOGITS
    ngdoc
    0.65
    міністра
    0.58
    Descripció
    0.57
     LoggerFactory
    0.56
     Vikipedi
    0.50
     tiguan
    0.49
    __*/
    0.49
     Wikispecies
    0.49
     uska
    0.48
    MLLoader
    0.48
    Activations Density 5.119%

    No Known Activations