© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58745
    Prev
    Next
    INDEX
    Explanations

    bond yields and maturity dates

    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_11_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
    i
    0.17
    \
    0.17
    Ин
    0.16
     इ
    0.16
    ser
    0.15
    Inventory
    0.15
     धारा
    0.15
    สำหรับ
    0.15
    イン
    0.15
     आहे
    0.15
    POSITIVE LOGITS
    افي
    0.21
    تي
    0.18
     deceiving
    0.17
    гро
    0.17
    يني
    0.17
    ائيل
    0.17
    циям
    0.16
    ﻲ
    0.16
    اري
    0.16
    йти
    0.16
    Activations Density 0.012%

    No Known Activations