© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254172
    Prev
    Next
    INDEX
    Explanations

    K

    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_56_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
     କରି
    0.39
     ligados
    0.39
    ่อง
    0.38
    Mutation
    0.38
     Kishan
    0.37
    pher
    0.37
    晒
    0.36
     Pall
    0.36
    _+
    0.36
    ผ่าน
    0.35
    POSITIVE LOGITS
    謁
    0.41
     gymn
    0.39
     building
    0.38
    building
    0.38
     ast
    0.37
     educating
    0.37
     Gymn
    0.36
    cyclic
    0.35
     asl
    0.35
     drin
    0.34
    Activations Density 0.000%

    No Known Activations