© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13477
    Prev
    Next
    INDEX
    Explanations

    references to the current time and limitations

    oai_token-act-pair · gemini-2.0-flash

    moment/now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     currently
    -0.58
     mergeFrom
    -0.55
    Currently
    -0.53
     Presently
    -0.52
     Currently
    -0.50
     diverti
    -0.50
    einander
    -0.50
     presently
    -0.49
     derzeit
    -0.48
    currently
    -0.48
    POSITIVE LOGITS
     calendriers
    0.65
    Portale
    0.64
     للمعارف
    0.54
     FontWeight
    0.52
    tanleria
    0.52
    Unmount
    0.50
    OnAdd
    0.50
    itinéraire
    0.49
     виправивши
    0.49
     Sigurd
    0.48
    Activations Density 9.280%

    No Known Activations