© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15573
    Prev
    Next
    INDEX
    Explanations

    a variety of structural elements, symbols, and formatting markers, possibly within code or specifically marked sections of text.

    oai_token-act-pair · gemini-2.0-flash

    mixed jumbled formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     fill
    -0.40
     المق
    -0.39
    dwell
    -0.37
     little
    -0.36
    put
    -0.34
     ple
    -0.33
    lesi
    -0.32
     sch
    -0.32
     Cle
    -0.32
     sleeper
    -0.32
    POSITIVE LOGITS
    存于互联网档案馆
    0.97
     <=",
    0.96
     transfieras
    0.94
     OFDb
    0.91
    RegistryLite
    0.91
     autorytatywna
    0.90
    SharedCtor
    0.90
    ViewFeatures
    0.90
     Normdatei
    0.90
     CreateTagHelper
    0.87
    Activations Density 4.876%

    No Known Activations