© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9017
    Prev
    Next
    INDEX
    Explanations

    Microsoft Active Directory and Apps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    فة
    2.39
    ی
    2.34
    ನಲ್ಲಿ
    2.10
    ्ह
    2.07
    cue
    1.95
    ixo
    1.94
    क
    1.92
    gang
    1.87
    ją
    1.87
    يير
    1.85
    POSITIVE LOGITS
    ع
    2.64
     jerk
    2.48
    ﻝ
    2.45
    可以
    2.39
    ीडियो
    2.30
    er
    2.28
    smile
    2.24
    ar
    2.22
     indiv
    2.20
    erent
    2.17
    Activations Density 0.049%

    No Known Activations