© 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. 14713
    Prev
    Next
    INDEX
    Explanations

    Spanish words mixed in with English and code

    oai_token-act-pair · gemini-2.0-flash

    programming and software

    np_max-act-logits · gemini-2.0-flash

    Spanish possessives

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Monfieur
    -1.29
     myſelf
    -1.16
     leaſt
    -1.14
     ſeveral
    -1.13
     Majefty
    -1.10
     pleaſure
    -1.09
     ſche
    -1.09
     HasFactory
    -1.09
     Shakspeare
    -1.08
     Jefus
    -1.07
    POSITIVE LOGITS
     in
    0.39
     an
    0.36
    q
    0.30
     car
    0.30
     i
    0.29
     t
    0.29
     cref
    0.29
     base
    0.28
     
    0.28
     Car
    0.28
    Activations Density 0.414%

    No Known Activations