© 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. 13462
    Prev
    Next
    INDEX
    Explanations

    proper names (people, places, organizations)

    oai_token-act-pair · gemini-2.0-flash

    proper names, titles

    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
    photobucket
    -0.64
    iprot
    -0.60
    PostInfinity
    -0.59
    帖最后由
    -0.57
    Alike
    -0.52
    offsetof
    -0.51
     urodz
    -0.50
     bParam
    -0.50
    شهاد
    -0.48
    BorderFactory
    -0.46
    POSITIVE LOGITS
    SpringRunner
    0.76
    IonicModule
    0.63
     مرئيه
    0.58
    aarrggbb
    0.57
     freeing
    0.54
    WebVitals
    0.54
    tableFuture
    0.54
    ">//
    0.53
    useNewUrlParser
    0.52
     OkHttpClient
    0.52
    Activations Density 5.665%

    No Known Activations