© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 55065
    Prev
    Next
    INDEX
    Explanations

    personal experience

    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_55_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
     വ്യത്യ
    0.42
     incorporate
    0.42
    donate
    0.42
    capture
    0.41
    Какой
    0.41
     下さい
    0.41
    Conversely
    0.40
     Conversely
    0.39
    ඈ
    0.39
    Maven
    0.38
    POSITIVE LOGITS
     got
    0.72
    Got
    0.68
     Got
    0.64
    got
    0.63
     insisted
    0.51
     turned
    0.50
     didn
    0.48
     GOT
    0.48
     agreed
    0.46
     didnt
    0.46
    Activations Density 0.006%

    No Known Activations