© 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. 128943
    Prev
    Next
    INDEX
    Explanations

    right?

    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
    Negative Logits
    ש
    0.93
    า
    0.82
    다
    0.82
    но
    0.81
    تهم
    0.80
    на
    0.80
    のかもし
    0.79
    as
    0.79
     Hye
    0.79
    त
    0.79
    POSITIVE LOGITS
    ۔
    1.14
    िंग
    0.96
    í
    0.95
    ating
    0.92
    ام
    0.88
     it
    0.86
     r
    0.86
    <0x0D>
    0.82
    hhh
    0.82
    ę
    0.82
    Activations Density 0.001%

    No Known Activations