© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2901
    Prev
    Next
    INDEX
    Explanations

    names of people and places, especially in France

    oai_token-act-pair · gemini-2.0-flash

    French names and prefixes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Anſ
    -0.92
     Shakspeare
    -0.90
     Houſe
    -0.88
     Majefty
    -0.87
     Efq
    -0.86
     Reſ
    -0.84
     Monfieur
    -0.82
     myſelf
    -0.81
     Diſ
    -0.77
     houſe
    -0.77
    POSITIVE LOGITS
     Jean
    0.54
    -
    0.54
     Val
    0.53
     Le
    0.51
     P
    0.48
     et
    0.47
    bourg
    0.47
     Che
    0.47
    val
    0.45
    tienne
    0.45
    Activations Density 2.444%

    No Known Activations