© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14249
    Prev
    Next
    INDEX
    Explanations

    the word "the" alone or in context with other words

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     (
    -0.58
    ,
    -0.54
     
    -0.47
     )
    -0.44
     to
    -0.44
     as
    -0.44
     a
    -0.44
     its
    -0.43
     The
    -0.43
    ↵↵
    -0.42
    POSITIVE LOGITS
     الحره
    1.16
    IUrlHelper
    1.10
     itſelf
    1.08
     case
    1.05
     pleaſure
    1.02
     myſelf
    1.00
    تقاوى
    1.00
     cauſe
    1.00
     насељу
    1.00
     المعيارى
    0.99
    Activations Density 6.525%

    No Known Activations