© 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. 7024
    Prev
    Next
    INDEX
    Explanations

    capitalized words (especially "The") in a string of words, and words that come before prepositions

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     CreateTagHelper
    -0.61
    Solución
    -0.60
    waitKey
    -0.55
    riwal
    -0.54
    MLLoader
    -0.54
      (
    -0.53
     Wiktionnaire
    -0.52
    oules
    -0.52
     فريبيس
    -0.52
     &___
    -0.51
    POSITIVE LOGITS
    ppard
    0.57
    FormTagHelper
    0.55
     препратки
    0.51
    LabelTagHelper
    0.50
    最低
    0.47
    utilisons
    0.47
     buka
    0.47
     Lowest
    0.47
    adpleegd
    0.46
     Moyen
    0.45
    Activations Density 1.845%

    No Known Activations