© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7635
    Prev
    Next
    INDEX
    Explanations

    the word 'the' following 'around'

    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
     World
    -2.19
    World
    -1.98
     WORLD
    -1.50
    WORLD
    -1.41
     Worlds
    -1.34
    ワールド
    -1.15
    Worlds
    -1.09
     Dunia
    -1.06
     Worldwide
    -1.05
     Mundial
    -0.99
    POSITIVE LOGITS
    ⓧ
    0.73
    iNdEx
    0.61
     himſelf
    0.57
    scriptcase
    0.55
     Приступљено
    0.54
     itſelf
    0.53
    createStatement
    0.52
     Sitten
    0.51
     كومونز
    0.51
     whoſe
    0.50
    Activations Density 4.768%

    No Known Activations