© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2070
    Prev
    Next
    INDEX
    Explanations

    instances of the word "I" or sentences spoken in first person

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    didSet
    -0.56
    ViewFeatures
    -0.53
    iastes
    -0.52
    Diweddarwch
    -0.51
    WindowConstants
    -0.50
     resourceCulture
    -0.49
     form
    -0.49
    mtrl
    -0.49
    protoimpl
    -0.49
    rafat
    -0.48
    POSITIVE LOGITS
     Мексичка
    0.59
    <bos>
    0.58
    Izvori
    0.55
     autorytatywna
    0.55
    -------------</
    0.52
     незавершена
    0.52
    RegressionTest
    0.51
     ویکی‌پدیا
    0.51
     Sú
    0.51
    فحة
    0.50
    Activations Density 10.912%

    No Known Activations