© 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. 15838
    Prev
    Next
    INDEX
    Explanations

    gibberish and code fragments

    oai_token-act-pair · gemini-2.0-flash

    Code and formulas

    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
     Peep
    -0.78
     McCull
    -0.75
     
    -0.75
     Osborne
    -0.72
     Loeb
    -0.71
     Rouse
    -0.71
     Zeke
    -0.70
     AIT
    -0.69
     Circulation
    -0.69
     Yak
    -0.68
    POSITIVE LOGITS
     Centennial
    0.67
     Holman
    0.66
     Floren
    0.59
    brano
    0.57
     Gallen
    0.57
     Klee
    0.56
     ujednoznacz
    0.55
     WWI
    0.51
     Botswana
    0.51
     schwar
    0.50
    Activations Density 5.554%

    No Known Activations