© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62534
    Prev
    Next
    INDEX
    Explanations

    common issues and speculation

    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_11_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
     monde
    0.46
     pa
    0.46
     releases
    0.46
     ovvero
    0.45
     pron
    0.45
    骧
    0.45
    rind
    0.44
    AD
    0.44
     ans
    0.43
     prominent
    0.43
    POSITIVE LOGITS
    哟
    0.52
    ید
    0.49
    يت
    0.48
    되어
    0.48
     filmpje
    0.47
     накопи
    0.47
    넹
    0.46
    ین
    0.45
    ਤਾ
    0.45
    що
    0.43
    Activations Density 0.000%

    No Known Activations