© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163711
    Prev
    Next
    INDEX
    Explanations

    first person pronoun followed by modal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zeta
    0.40
     seism
    0.39
     seascape
    0.37
     industrielle
    0.37
    ᑉ
    0.37
    <b>
    0.36
     crisis
    0.36
     ×
    0.36
     maison
    0.36
    ustic
    0.36
    POSITIVE LOGITS
     Thực
    0.46
    CLionProjects
    0.46
    ای
    0.46
     নিয়ে
    0.44
    laşı
    0.43
    ために
    0.43
     Milliarden
    0.43
    Loads
    0.43
    ف
    0.43
     جهانی
    0.43
    Activations Density 0.019%

    No Known Activations