© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2870
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers related to software.

    oai_token-act-pair · gemini-2.0-flash

    foreign prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     myſelf
    -1.10
     itſelf
    -1.04
    ſelf
    -1.01
     Anſ
    -1.01
     Theſe
    -0.99
     Eſ
    -0.95
     Diſ
    -0.94
    ſelves
    -0.91
     Reſ
    -0.91
     Monfieur
    -0.90
    POSITIVE LOGITS
     de
    0.63
     aus
    0.59
     pour
    0.57
     por
    0.56
     um
    0.55
     per
    0.54
     las
    0.54
     des
    0.52
     do
    0.52
     en
    0.52
    Activations Density 2.921%

    No Known Activations