© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14927
    Prev
    Next
    INDEX
    Explanations

    words about light beams, optics, and related technology

    oai_token-act-pair · gemini-2.0-flash

    light manipulation

    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
     useParams
    -0.53
     betweenstory
    -0.51
     Waray
    -0.51
     وتسجيلات
    -0.51
    IsContent
    -0.49
    efeller
    -0.49
     jLabel
    -0.49
     незавершена
    -0.49
     nakalista
    -0.48
     himo
    -0.47
    POSITIVE LOGITS
     peindre
    0.65
    Билгалдахарш
    0.57
     couverts
    0.57
     verksamhet
    0.56
     réparation
    0.55
     tombé
    0.54
     Pank
    0.54
     couvert
    0.54
     AttributeSet
    0.54
    Зноскі
    0.52
    Activations Density 6.864%

    No Known Activations