© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13730
    Prev
    Next
    INDEX
    Explanations

    first person statements using "I" with auxiliary verbs "do", "would", or contractions with 't

    oai_token-act-pair · gemini-2.0-flash

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     kaarangay
    -0.62
     Ingredient
    -0.58
    ậy
    -0.58
    andExpect
    -0.57
     attendu
    -0.54
     pageContext
    -0.54
    asteroide
    -0.53
     immunoglobulin
    -0.53
     shouldBe
    -0.53
    othelioma
    -0.52
    POSITIVE LOGITS
    ")->
    0.67
     did
    0.62
     few
    0.60
    .'”
    0.58
    ногие
    0.58
    HtmlAttribute
    0.58
    UGE
    0.57
    ناك
    0.57
    ')")
    0.57
    mergeFrom
    0.56
    Activations Density 2.002%

    No Known Activations