© 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. 314
    Prev
    Next
    INDEX
    Explanations

    code related to vector loading

    oai_token-act-pair · gemini-2.0-flash

    Code and data structures

    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
     autorytatywna
    -1.14
     AssemblyCulture
    -1.08
    Personensuche
    -1.06
    تقاوى
    -0.98
     Roskov
    -0.94
     OFDb
    -0.93
     lenker
    -0.92
     Италијани
    -0.91
    存于互联网档案馆
    -0.90
     CreateTagHelper
    -0.90
    POSITIVE LOGITS
     N
    0.48
    la
    0.47
    lo
    0.46
      
    0.42
       
    0.41
     Q
    0.40
     U
    0.40
     No
    0.40
     T
    0.39
    ↵
    0.39
    Activations Density 5.605%

    No Known Activations