© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136354
    Prev
    Next
    INDEX
    Explanations

    100% Real Pict

    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_12_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
     organisations
    0.42
     megs
    0.42
     s
    0.41
     tincture
    0.41
    s
    0.41
     soreness
    0.41
     {
    0.39
     slic
    0.39
     두
    0.39
     thorns
    0.39
    POSITIVE LOGITS
     ম্যাজিস্ট্রেট
    0.41
     sujetos
    0.40
     بخش
    0.39
     Од
    0.39
     গুরুত্বপূর্ণ
    0.38
     функция
    0.38
     keadaan
    0.37
     Исто
    0.37
    uerra
    0.37
    erde
    0.37
    Activations Density 0.000%

    No Known Activations