© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9412
    Prev
    Next
    INDEX
    Explanations

    code and code-related files (such as libraries) in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    Code related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    abestanden
    -0.61
     initComponents
    -0.59
     CreateTagHelper
    -0.57
    ScopeManager
    -0.53
    
    -0.49
    ViewFeatures
    -0.46
    RequiresApi
    -0.46
     useDispatch
    -0.45
    SOUNDBITE
    -0.45
    évaluateur
    -0.45
    POSITIVE LOGITS
    rsiniz
    0.71
    /*
    0.65
    plained
    0.60
     Customization
    0.60
     Nazareth
    0.59
     USA
    0.57
     customization
    0.57
     pauv
    0.57
    __':
    0.57
     semula
    0.56
    Activations Density 3.347%

    No Known Activations