© 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. 167972
    Prev
    Next
    INDEX
    Explanations

    numbers listed after 2, 3

    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
     churches
    0.37
     dve
    0.36
    êt
    0.36
    辏
    0.36
    下跌
    0.35
    ioribus
    0.35
    ibilités
    0.34
    getR
    0.34
    GET
    0.34
     δύο
    0.34
    POSITIVE LOGITS
     кушымта
    0.41
     jai
    0.41
     если
    0.41
    পর্য
    0.39
     قام
    0.39
     interrogate
    0.38
     ladd
    0.37
    崖
    0.37
    澥
    0.37
    หาก
    0.36
    Activations Density 0.000%

    No Known Activations