© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161226
    Prev
    Next
    INDEX
    Explanations

    diversity statements

    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_31_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
    事が
    0.46
     pole
    0.36
    ์
    0.35
    −
    0.35
    jan
    0.34
    сад
    0.34
    /#{
    0.34
    λαν
    0.34
    achs
    0.34
     कहां
    0.33
    POSITIVE LOGITS
     همچنین
    0.39
    Kons
    0.38
    ⽤
    0.36
     এটাও
    0.36
    Cons
    0.35
    還可以
    0.35
    ুয়াল
    0.34
     conso
    0.34
    스럽
    0.34
    还可以
    0.33
    Activations Density 0.029%

    No Known Activations