© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83174
    Prev
    Next
    INDEX
    Explanations

    fade

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    पीएफ
    0.46
    বান
    0.42
     নিয়েছে
    0.41
     列
    0.40
    валь
    0.39
     takım
    0.39
     உடை
    0.39
    列
    0.39
    Tar
    0.39
    ㄩ
    0.39
    POSITIVE LOGITS
     Fade
    0.44
    fade
    0.41
     fading
    0.40
     Ke
    0.40
     ke
    0.40
    Fade
    0.39
     fade
    0.37
     Kappa
    0.36
     milj
    0.36
     Кей
    0.36
    Activations Density 0.000%

    No Known Activations