© 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. 34935
    Prev
    Next
    INDEX
    Explanations

    live broadcast or stream

    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
     demikian
    0.61
     unaccompanied
    0.55
    </sup>
    0.55
    nger
    0.54
    ll
    0.53
    ):
    0.53
    ns
    0.51
     quantum
    0.51
     انت
    0.51
    >.
    0.51
    POSITIVE LOGITS
     Londres
    0.56
    на
    0.54
     Hôtel
    0.51
    োডে
    0.50
    ॉन
    0.50
    питы
    0.49
    是什么
    0.49
     Mene
    0.48
    acidade
    0.48
    다른
    0.48
    Activations Density 0.002%

    No Known Activations