© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103997
    Prev
    Next
    INDEX
    Explanations

    Thai diacritics and Korean words

    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_1_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
    та
    1.15
    ா
    1.13
    ا
    1.06
    ла
    1.05
     heen
    1.03
    á
    1.02
    :
    1.02
    的过程中
    1.00
    اية
    0.99
    ,.
    0.98
    POSITIVE LOGITS
     이미
    1.27
    ید
    1.26
    위
    1.16
    H
    1.12
    持つ
    1.09
    할
    1.09
     시
    1.07
     회
    1.05
     고
    1.03
    dac
    1.03
    Activations Density 0.000%

    No Known Activations