© 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. 3987
    Prev
    Next
    INDEX
    Explanations

    words and short phrases in languages other than English or that look foreign, especially Italian

    oai_token-act-pair · 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
     lo
    -0.57
     l
    -0.47
     for
    -0.46
    Carriera
    -0.41
     li
    -0.39
     il
    -0.38
     fi
    -0.38
     Fi
    -0.38
    $_['
    -0.37
    haer
    -0.36
    POSITIVE LOGITS
     itſelf
    1.01
     myſelf
    0.96
     Monfieur
    0.91
     Theſe
    0.87
     Efq
    0.86
     againſt
    0.85
     Jefus
    0.85
     becauſe
    0.84
     raiſ
    0.84
     himſelf
    0.82
    Activations Density 2.585%

    No Known Activations