© 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. 9377
    Prev
    Next
    INDEX
    Explanations

    code errors, exceptions and debugging statements

    oai_token-act-pair · gemini-2.0-flash

    code/software errors

    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
     wrong
    -0.60
     bad
    -0.58
     inefficient
    -0.58
     inaccurate
    -0.58
     inefficiency
    -0.58
     ineligible
    -0.56
     ineffective
    -0.55
    مراجع
    -0.54
     faulty
    -0.54
     malheureux
    -0.54
    POSITIVE LOGITS
    Географи
    0.61
    routeProvider
    0.60
    openzeppelin
    0.52
    ImageContext
    0.50
     незавершена
    0.48
    stateProvider
    0.48
    ConverterFactory
    0.47
    ValueStyle
    0.47
    RectangleBorder
    0.46
     IBOutlet
    0.46
    Activations Density 3.332%

    No Known Activations