© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8091
    Prev
    Next
    INDEX
    Explanations

    technical language around scientific measurements.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     שוליים
    -0.71
     Roskov
    -0.69
     >=",
    -0.69
    FormTagHelper
    -0.68
    Zacks
    -0.64
    IVEREF
    -0.62
     StatefulWidget
    -0.62
    SourceChecksum
    -0.62
     NSCoder
    -0.60
     OnInit
    -0.58
    POSITIVE LOGITS
     Majefty
    0.59
     Monfieur
    0.57
     Jefus
    0.56
     Theſe
    0.54
     mixte
    0.53
     Efq
    0.52
    AddTagHelper
    0.51
     bezoek
    0.50
     ſeveral
    0.49
     againſt
    0.49
    Activations Density 0.986%

    No Known Activations