© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16197
    Prev
    Next
    INDEX
    Explanations

    first person pronouns such as "I" and "me" in various languages and contexts

    oai_token-act-pair · gemini-2.0-flash

    I, me, my

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.66
    ValueStyle
    -0.65
     resourceCulture
    -0.57
    Chham
    -0.57
    addCriterion
    -0.57
    ThroughAttribute
    -0.57
    Билгалдахарш
    -0.56
     autorytatywna
    -0.56
    Collegamenti
    -0.54
    msgSender
    -0.53
    POSITIVE LOGITS
     ویکی‌پدیا
    0.58
    ="@+
    0.54
    Nad
    0.53
    UnitTesting
    0.51
     Abandon
    0.50
     Accueil
    0.49
     fibrillation
    0.49
     burl
    0.48
     informée
    0.48
    يميديا
    0.47
    Activations Density 3.781%

    No Known Activations