© 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. 8028
    Prev
    Next
    INDEX
    Explanations

    gossip or news about celebrities.

    oai_token-act-pair · gemini-2.0-flash

    quits

    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
    nestjs
    -0.43
     notare
    -0.41
    hner
    -0.41
     δη
    -0.38
     NgModule
    -0.38
    싱
    -0.38
     Cir
    -0.37
    olah
    -0.37
    Tazama
    -0.37
    maries
    -0.36
    POSITIVE LOGITS
     snippetHide
    0.86
    PointerException
    0.77
    /*
    0.76
    ItemBackground
    0.74
     chi̍t
    0.73
    IVEREF
    0.70
    UserScript
    0.69
    djangoproject
    0.67
     Normdatei
    0.66
     DataLoader
    0.66
    Activations Density 1.942%

    No Known Activations