© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16135
    Prev
    Next
    INDEX
    Explanations

    legal and financial jargon

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     vu
    -0.48
     off
    -0.44
     diagnostic
    -0.43
    PointerException
    -0.43
     at
    -0.43
    NEYS
    -0.42
     vera
    -0.41
    ılan
    -0.41
     held
    -0.41
     á
    -0.41
    POSITIVE LOGITS
    XmlAccessorType
    0.79
     Shakspeare
    0.77
    Obrázky
    0.76
     myſelf
    0.75
    Personendaten
    0.75
    клопе
    0.72
    invokeLater
    0.65
    XmlType
    0.65
    ########.
    0.65
     Muses
    0.65
    Activations Density 42.024%

    No Known Activations