© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102959
    Prev
    Next
    INDEX
    Explanations

    Eros or Erosive

    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_1_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
     to
    1.89
     on
    1.72
    ن
    1.59
    ل
    1.48
     by
    1.45
     has
    1.44
    я
    1.41
    л
    1.35
    ли
    1.34
     $
    1.26
    POSITIVE LOGITS
    T
    1.37
    that
    1.16
    W
    1.13
    AR
    0.98
    ata
    0.98
    O
    0.98
    AL
    0.97
    ba
    0.97
    V
    0.96
    mek
    0.96
    Activations Density 0.001%

    No Known Activations