© 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. 137185
    Prev
    Next
    INDEX
    Explanations

    technology and code

    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
    沌
    0.45
    renders
    0.41
    ജ്ഞ
    0.41
     Fach
    0.40
    fertigt
    0.40
    rote
    0.39
     Oper
    0.39
     Hochsch
    0.39
     herd
    0.39
    ombok
    0.38
    POSITIVE LOGITS
    ього
    0.38
    उन
    0.37
    绫
    0.37
    ಿಂದ
    0.37
    ौन
    0.36
    autogui
    0.36
     লক্ষ
    0.36
    ὅ
    0.36
     uncut
    0.36
    راً
    0.35
    Activations Density 0.021%

    No Known Activations