© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11350
    Prev
    Next
    INDEX
    Explanations

    a mix of Serbian words related to email, sexual content, and French words related to computer screens

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     picioare
    -1.64
     viață
    -1.64
     maș
    -1.47
     creș
    -1.45
     obicei
    -1.45
     argint
    -1.43
     nimic
    -1.39
     uș
    -1.38
     fapt
    -1.37
     față
    -1.35
    POSITIVE LOGITS
    <bos>
    0.89
    تقاوى
    0.88
     huom
    0.81
     coû
    0.79
    enumi
    0.78
    
    0.77
    parsedMessage
    0.76
     mukana
    0.73
     Савезне
    0.73
     lisäksi
    0.73
    Activations Density 0.611%

    No Known Activations