© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13438
    Prev
    Next
    INDEX
    Explanations

    instances where an argument or case is being made.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     arguments
    -2.50
     argument
    -2.48
     Argument
    -2.30
     Arguments
    -2.30
    argument
    -2.28
     argue
    -2.20
    Argument
    -2.13
     arg
    -2.11
    arguments
    -2.11
     argued
    -2.08
    POSITIVE LOGITS
     geladeira
    0.54
    ніципалі
    0.54
     prefeitura
    0.53
    Aholisi
    0.52
     refrigerador
    0.50
    bentukan
    0.46
    kolwiek
    0.46
     rafraî
    0.45
    Sonder
    0.44
    ковник
    0.44
    Activations Density 2.638%

    No Known Activations