© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13521
    Prev
    Next
    INDEX
    Explanations

    a variety of terms, including legal phrases, medical terms, references to satan, numbers, some verbs ending in "ing", and words ending in "al"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Вікіпе
    -0.79
    findpost
    -0.70
     <<<<<<<<<<<<<<
    -0.68
    RefNanny
    -0.67
     мәкал
    -0.67
    Personensuche
    -0.66
     FetchType
    -0.65
     незавершена
    -0.64
     onCreateView
    -0.63
    SharedDtor
    -0.63
    POSITIVE LOGITS
     sideline
    0.46
    らかに
    0.43
     australis
    0.43
     dalamnya
    0.39
     Griechen
    0.38
     Municipalidad
    0.38
     Gators
    0.37
    Mid
    0.37
    Adverse
    0.37
    spaceBetween
    0.37
    Activations Density 4.857%

    No Known Activations