© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 62958
    Prev
    Next
    INDEX
    Explanations

    -

    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_46_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
    Featuring
    0.40
    ექ
    0.40
     चाहि
    0.39
     ພວກເຮົາ
    0.38
    Neuro
    0.38
     neuro
    0.38
     हाइड्रो
    0.38
    プロ
    0.37
    持
    0.37
    謃
    0.37
    POSITIVE LOGITS
    inte
    0.38
    jd
    0.37
     Nikola
    0.37
     Cal
    0.35
     Bled
    0.35
     Henry
    0.34
    lices
    0.34
    헨
    0.34
    fd
    0.34
     BR
    0.34
    Activations Density 0.001%

    No Known Activations