© 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. 35003
    Prev
    Next
    INDEX
    Explanations

    lively tunes and discussion

    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
    hitth
    0.55
    гийн
    0.54
    RESOLUTION
    0.54
    ロジー
    0.54
    DanhMucSP
    0.53
     unvaccinated
    0.52
    し
    0.52
     தாம்
    0.51
     expir
    0.51
     trunc
    0.51
    POSITIVE LOGITS
    </b>
    0.66
    </code>
    0.66
    </strong>
    0.63
    ene
    0.60
    ante
    0.58
    ated
    0.57
    ας
    0.54
    anoj
    0.53
    </h1>
    0.53
    ation
    0.53
    Activations Density 0.001%

    No Known Activations