© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14257
    Prev
    Next
    INDEX
    Explanations

    a mix of verbs, certain adjectives, and words in a non-English language related to legal terms and privacy

    oai_token-act-pair · gemini-2.0-flash

    mixed languages and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Portale
    -0.91
     myſelf
    -0.89
     itſelf
    -0.88
     pleaſure
    -0.85
     diſt
    -0.83
     uſed
    -0.81
     purpoſe
    -0.81
     poffe
    -0.80
     fubject
    -0.79
    IsContent
    -0.77
    POSITIVE LOGITS
    ان
    0.48
    nya
    0.42
    RLock
    0.42
    ne
    0.42
    必
    0.41
    ниц
    0.41
    ہ
    0.39
    تي
    0.39
    ongan
    0.38
    ka
    0.37
    Activations Density 0.788%

    No Known Activations