© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11360
    Prev
    Next
    INDEX
    Explanations

    code blocks, specifically looking for closing curly braces followed by a newline and indentation

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     otomatig
    -0.68
     ThemeData
    -0.66
    evos
    -0.61
    ViewFeatures
    -0.60
    SharedDtor
    -0.59
     فريبيس
    -0.57
    RegistryLite
    -0.56
    новниш
    -0.56
     مُعرِّف
    -0.55
     useStyles
    -0.55
    POSITIVE LOGITS
    setw
    0.47
     overboard
    0.46
    цыі
    0.46
    égard
    0.45
     OGSÅ
    0.45
    DeleteBehavior
    0.43
     Taub
    0.42
    ể
    0.42
    contentLoaded
    0.42
    }{#
    0.42
    Activations Density 1.361%

    No Known Activations