© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154518
    Prev
    Next
    INDEX
    Explanations

    bell door

    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_50_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
     bell
    2.58
    Bell
    2.41
     Bell
    2.38
     bells
    2.38
     BELL
    2.25
    bell
    2.22
    BELL
    2.17
     Bells
    2.14
    bells
    1.91
    铃
    1.73
    POSITIVE LOGITS
    ॉफ
    0.38
    ipient
    0.37
     jurusan
    0.37
    Hc
    0.36
    juv
    0.36
    hne
    0.35
     непро
    0.35
     Дуб
    0.35
     لوی
    0.35
     אַ
    0.34
    Activations Density 0.001%

    No Known Activations