© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14453
    Prev
    Next
    INDEX
    Explanations

    words related to prepositions and the French language

    oai_token-act-pair · gemini-2.0-flash

    French language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Erde
    -0.42
     svůj
    -0.41
     ред
    -0.41
    րջ
    -0.40
     gerekir
    -0.40
    zyn
    -0.40
    未必
    -0.38
     bezpiecz
    -0.38
     darah
    -0.37
    äumt
    -0.37
    POSITIVE LOGITS
    SBATCH
    0.81
    MemoryWarning
    0.78
    Tikang
    0.77
    पया
    0.75
    jsxFileName
    0.74
     firebaseConfig
    0.74
    EndProject
    0.72
     <<<<<<<<<<<<<<
    0.72
    adaptiveStyles
    0.71
    ListItemIcon
    0.71
    Activations Density 0.991%

    No Known Activations