© 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. 15228
    Prev
    Next
    INDEX
    Explanations

    decimal numbers

    oai_token-act-pair · gemini-2.0-flash

    Number 8

    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
    fromnode
    -0.61
     ExecuteAsync
    -0.59
     SIX
    -0.58
    FIVE
    -0.55
     six
    -0.55
     Six
    -0.54
    six
    -0.54
     five
    -0.54
    五
    -0.52
    SIX
    -0.51
    POSITIVE LOGITS
     eighth
    0.80
    8
    0.79
     Eighth
    0.77
     Eight
    0.69
     eight
    0.68
    NameInMap
    0.58
     huit
    0.57
     eighties
    0.57
     Eighty
    0.57
    第八
    0.56
    Activations Density 3.862%

    No Known Activations