© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51606
    Prev
    Next
    INDEX
    Explanations

    Exploited Children (NCMEC)

    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_10_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
    s
    0.32
    lés
    0.32
    lä
    0.29
     మ
    0.29
    iem
    0.27
    lapping
    0.27
     ما
    0.27
     आता
    0.27
    raham
    0.27
     क्षेत्रा
    0.27
    POSITIVE LOGITS
    ERSHIP
    0.28
    ﻙ
    0.28
     userInfo
    0.28
    Bedroom
    0.28
     comboBox
    0.27
     он
    0.27
     Adjustment
    0.27
    <0x0D>
    0.27
    ន
    0.26
    ciendo
    0.26
    Activations Density 0.000%

    No Known Activations