© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15232
    Prev
    Next
    INDEX
    Explanations

    the word "or", especially when it is near a time duration

    oai_token-act-pair · gemini-2.0-flash

    say "so" or "two" 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_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
     or
    -1.00
     или
    -0.88
    或
    -0.80
     atau
    -0.77
     hoặc
    -0.76
    或者
    -0.76
     nebo
    -0.72
     یا
    -0.70
     eller
    -0.69
     或
    -0.69
    POSITIVE LOGITS
     so
    0.76
    principalColumn
    0.74
     however
    0.68
    ucchini
    0.62
     transfieras
    0.61
     slightly
    0.59
     pinulongan
    0.59
     оригіналу
    0.59
    chenta
    0.58
    χος
    0.57
    Activations Density 0.897%

    No Known Activations