© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206716
    Prev
    Next
    INDEX
    Explanations

    sent / sending

    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_6_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
    erosion
    0.97
    ا
    0.94
    महल
    0.92
    inin
    0.90
    ون
    0.89
    ering
    0.89
    illation
    0.88
    ation
    0.88
    inh
    0.88
    en
    0.85
    POSITIVE LOGITS
    ك
    1.11
     posibil
    1.02
     lanç
    0.96
     pregunt
    0.96
     uczni
    0.96
     for
    0.95
    ف
    0.93
     {
    0.91
     jeste
    0.91
     validar
    0.91
    Activations Density 0.008%

    No Known Activations