© 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. 3946
    Prev
    Next
    INDEX
    Explanations

    the token "Py" followed by other characters or numbers

    oai_token-act-pair · gemini-2.0-flash

    py

    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
    
    -1.00
    AndEndTag
    -0.94
    aarrggbb
    -0.84
     beginnetje
    -0.83
    GEBURTSDATUM
    -0.83
    Referensi
    -0.83
    parsedMessage
    -0.79
    Дереккөздер
    -0.76
     дописавши
    -0.76
    verwijspagina
    -0.75
    POSITIVE LOGITS
    lay
    0.43
    lot
    0.40
    meld
    0.40
    oten
    0.39
    olen
    0.39
    ké
    0.38
     sor
    0.37
    Law
    0.37
    ำ
    0.37
    dan
    0.36
    Activations Density 1.305%

    No Known Activations