© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 587
    Prev
    Next
    INDEX
    Explanations

    Chinese words and names, likely related to website navigation or elements

    oai_token-act-pair · gemini-2.0-flash

    code/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     in
    -0.59
     on
    -0.56
     A
    -0.54
     "
    -0.50
     Al
    -0.49
     An
    -0.49
     F
    -0.48
     van
    -0.48
     
    -0.47
     In
    -0.46
    POSITIVE LOGITS
    AndEndTag
    1.39
     صوتيه
    1.32
     betweenstory
    1.18
     AssemblyCulture
    1.13
     pleaſure
    1.11
     CreateTagHelper
    1.05
    GEBURTSDATUM
    1.05
     виправивши
    1.05
    Personensuche
    1.05
     purpoſe
    1.04
    Activations Density 0.864%

    No Known Activations