© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16326
    Prev
    Next
    INDEX
    Explanations

    expressions of incredulity, medical terminology, and phrases about economics, race, or personal choice.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    TLDR
    -0.69
    stdint
    -0.66
    gnancy
    -0.65
     curated
    -0.63
     impactful
    -0.63
    LEVANT
    -0.61
     arguably
    -0.60
    nullptr
    -0.59
    logrus
    -0.59
     relatable
    -0.59
    POSITIVE LOGITS
     daß
    0.96
     läßt
    0.93
     muß
    0.93
     müßte
    0.82
     Daß
    0.80
     idéia
    0.77
     mußte
    0.75
     mußten
    0.75
     يتيمه
    0.71
     kasarigan
    0.69
    Activations Density 7.788%

    No Known Activations