© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48037
    Prev
    Next
    INDEX
    Explanations

    private communications and interactions

    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_31_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
     পত্রিকায়
    0.44
     vü
    0.38
    螺
    0.37
    打印
    0.36
    ^{*}}
    0.36
    覧
    0.35
    ίδα
    0.35
    漪
    0.35
    ádza
    0.35
    ামা
    0.34
    POSITIVE LOGITS
     privately
    0.60
     verbally
    0.47
     private
    0.43
     persuas
    0.41
     secretly
    0.41
     supporting
    0.41
     confided
    0.41
     privé
    0.40
    reserve
    0.39
     reserve
    0.39
    Activations Density 0.023%

    No Known Activations