© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 57572
    Prev
    Next
    INDEX
    Explanations

    Raman spectroscopy or Ramanujan

    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_2_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
    (
    1.51
    ри
    1.46
    -
    1.39
    은
    1.19
    1.18
    ס
    1.16
    是
    1.07
    을
    1.05
    1.05
    도
    0.98
    POSITIVE LOGITS
    z
    1.26
    c
    1.22
    ма
    1.16
     açık
    1.13
     a
    1.05
    g
    1.04
    pesar
    1.02
     .
    1.02
     maravill
    1.01
    don
    1.00
    Activations Density 0.000%

    No Known Activations