© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2702
    Prev
    Next
    INDEX
    Explanations

    words related to intent and the law

    oai_token-act-pair · gemini-2.0-flash

    intention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     intentional
    -0.81
     intentionally
    -0.79
     purposefully
    -0.76
     purposely
    -0.75
    MemoryWarning
    -0.74
     deliberately
    -0.72
     deliberate
    -0.64
    故意
    -0.63
    特意
    -0.63
    刻意
    -0.63
    POSITIVE LOGITS
     aveug
    0.56
     fidèles
    0.54
    __);
    0.52
    AndEndTag
    0.52
     företag
    0.48
     Accesat
    0.47
     ویکی‌آمباردا
    0.47
     Acceptable
    0.47
     hjemme
    0.47
     fidèle
    0.47
    Activations Density 32.067%

    No Known Activations