© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11822
    Prev
    Next
    INDEX
    Explanations

    a mix of words in different languages (Portuguese, Spanish, French) related to programming, comparisons, and conversational filler

    oai_token-act-pair · gemini-2.0-flash

    more

    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
     myſelf
    -0.98
     itſelf
    -0.87
     Efq
    -0.86
     pleaſure
    -0.85
     becauſe
    -0.84
     Monfieur
    -0.84
     فريبيس
    -0.82
     ་་
    -0.81
     fubject
    -0.81
     reaſon
    -0.81
    POSITIVE LOGITS
     long
    0.50
     apa
    0.47
    OLD
    0.47
     fast
    0.46
     Old
    0.46
    ResumeLayout
    0.45
     quick
    0.45
     high
    0.45
    haus
    0.44
     large
    0.44
    Activations Density 0.337%

    No Known Activations