© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16076
    Prev
    Next
    INDEX
    Explanations

    words denoting legal or scientific writing conventions, as well as instances and examples

    oai_token-act-pair · gemini-2.0-flash

    examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    mybatisplus
    -0.88
    原始内容存档于
    -0.84
     Italijanski
    -0.80
     MainAxisSize
    -0.80
    źródło
    -0.77
    Autoritní
    -0.75
     autorytatywna
    -0.74
     Roskov
    -0.74
     purpoſe
    -0.73
     Efq
    -0.73
    POSITIVE LOGITS
    forRoot
    0.56
    ,
    0.55
     to
    0.52
     names
    0.48
     objects
    0.48
     abiti
    0.47
     vestiti
    0.47
     links
    0.46
     ideas
    0.46
     steps
    0.46
    Activations Density 6.048%

    No Known Activations