© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10249
    Prev
    Next
    INDEX
    Explanations

    sentences where someone can't do something

    oai_token-act-pair · gemini-2.0-flash

    t or cannot

    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
     للمعارف
    -0.93
    存于互联网档案馆
    -0.90
    تقاوى
    -0.87
     Theſe
    -0.86
     AssemblyCulture
    -0.83
    حياته
    -0.82
     EconPapers
    -0.82
     Wiktionnaire
    -0.78
     HasFactory
    -0.77
     AssemblyProduct
    -0.75
    POSITIVE LOGITS
     very
    0.59
     just
    0.50
     Very
    0.48
    Very
    0.47
     be
    0.46
     list
    0.45
     sk
    0.44
     balance
    0.44
    very
    0.44
     develop
    0.43
    Activations Density 8.177%

    No Known Activations