© 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. 7994
    Prev
    Next
    INDEX
    Explanations

    words that have to do with how objects fit together.

    oai_token-act-pair · gemini-2.0-flash

    Storage/housing of items

    np_max-act · 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
     access
    -0.42
     sem
    -0.42
     dé
    -0.42
     plan
    -0.41
     pour
    -0.41
    .
    -0.39
     спро
    -0.39
     прямо
    -0.38
     area
    -0.38
     -
    -0.38
    POSITIVE LOGITS
     EconPapers
    1.23
    parsedMessage
    1.05
    writeFieldEnd
    1.01
    AndEndTag
    1.00
    DockStyle
    0.96
    tvguidetime
    0.94
     pleaſure
    0.94
    principalColumn
    0.93
    WebVitals
    0.91
     itſelf
    0.89
    Activations Density 0.695%

    No Known Activations