© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12379
    Prev
    Next
    INDEX
    Explanations

    code programming blocks, license comments, and preprocessor directives

    oai_token-act-pair · gemini-2.0-flash

    /*

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     المعيارى
    -0.70
     myſelf
    -0.68
     للمعارف
    -0.66
     itſelf
    -0.65
     ་་
    -0.63
     Efq
    -0.63
    RefNanny
    -0.61
    ſelves
    -0.60
    WaitGroup
    -0.59
     gawas
    -0.58
    POSITIVE LOGITS
    тара
    0.52
     General
    0.49
    ValueStyle
    0.49
     propósito
    0.47
     allmän
    0.46
     Wider
    0.45
     ancha
    0.45
     tombé
    0.45
     wide
    0.45
     Wide
    0.44
    Activations Density 1.546%

    No Known Activations