© 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-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171672
    Prev
    Next
    INDEX
    Explanations

    proper nouns like Shivaji, Sultan, Quan

    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_20_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
    ەت
    0.48
     تھیں
    0.47
     poziom
    0.45
    ('>
    0.45
    ቶ
    0.45
    ەتی
    0.44
    AutoHide
    0.43
    像素
    0.42
    ">>
    0.42
     tessuto
    0.41
    POSITIVE LOGITS
     M
    0.47
     diariamente
    0.47
     Pag
    0.45
     preferred
    0.44
     regularly
    0.44
     оптима
    0.43
    娄
    0.43
     outlines
    0.41
     Informations
    0.41
    ใส
    0.41
    Activations Density 0.000%

    No Known Activations