© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4091
    Prev
    Next
    INDEX
    Explanations

    a very specific, formulaic, podcast introduction

    oai_token-act-pair · gemini-2.0-flash

    articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    XmlAccessType
    -0.68
    /*
    -0.67
     للمعارف
    -0.64
    tagHelperRunner
    -0.63
    NOPQRST
    -0.62
     مشين
    -0.61
    TintMode
    -0.61
    UnusedPrivate
    -0.59
    PYX
    -0.57
     препратки
    -0.56
    POSITIVE LOGITS
     jelas
    0.56
     kerugian
    0.56
     pertes
    0.54
    iography
    0.52
     plomo
    0.52
     venganza
    0.51
     liderazgo
    0.50
    setDo
    0.50
    Web
    0.50
    TV
    0.49
    Activations Density 10.370%

    No Known Activations