© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    the words "to" and "try" and contractions ending in 't'

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     noqa
    -0.62
    .*")]
    -0.54
    basicConfig
    -0.52
    AlterField
    -0.51
    ParallelGroup
    -0.51
    matchCondition
    -0.49
    GEBURTS
    -0.49
     Pristupljeno
    -0.49
    imwrite
    -0.48
    AddHtmlAttribute
    -0.48
    POSITIVE LOGITS
     betweenstory
    0.61
    انيف
    0.58
     AppColors
    0.56
    UIControlState
    0.50
    tula
    0.49
    asilan
    0.49
    ℤ
    0.49
    ː
    0.49
    sior
    0.47
     dolci
    0.47
    Activations Density 5.132%

    No Known Activations