© 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. 10536
    Prev
    Next
    INDEX
    Explanations

    text likely to come from conversations in French.

    oai_token-act-pair · gemini-2.0-flash

    French language

    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
     createState
    -0.54
    تقاوى
    -0.48
     spectateurs
    -0.48
     Signalez
    -0.47
    FromArray
    -0.45
     en
    -0.43
    jącej
    -0.40
    żej
    -0.40
    हाय
    -0.39
     au
    -0.39
    POSITIVE LOGITS
    IsContent
    0.75
    saraba
    0.70
    Jereo
    0.62
    tagext
    0.60
    ExecuteReader
    0.59
    parsedMessage
    0.58
    StoryboardSegue
    0.57
     gainera
    0.57
    SBATCH
    0.57
    RectangleBorder
    0.57
    Activations Density 0.393%

    No Known Activations