© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10514
    Prev
    Next
    INDEX
    Explanations

    first person conjugations of the verb "to have/be" plus a few words that often appear nearby in French or Spanish

    oai_token-act-pair · 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
     estekak
    -1.03
     NUKAT
    -0.95
     المعيارى
    -0.89
     >=",
    -0.85
     Theſe
    -0.84
     Dens
    -0.84
     kasarigan
    -0.80
     nakalista
    -0.80
    )++;
    -0.78
    BibitemShut
    -0.78
    POSITIVE LOGITS
     
    0.50
     or
    0.49
     as
    0.49
     al
    0.49
     pre
    0.45
    ParallelGroup
    0.44
     el
    0.43
     a
    0.43
    ,
    0.43
     se
    0.42
    Activations Density 0.248%

    No Known Activations