© 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. 168052
    Prev
    Next
    INDEX
    Explanations

    years and data tables

    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
     ಪ್ರಾ
    0.39
    nungs
    0.38
    반
    0.36
    sad
    0.36
    ffff
    0.36
    ion
    0.36
    stopping
    0.36
    bonne
    0.36
    innie
    0.36
    toolkit
    0.36
    POSITIVE LOGITS
    лас
    0.37
     ఆ
    0.36
     wel
    0.36
     telegram
    0.36
     rece
    0.35
    수록
    0.35
     antibiotic
    0.34
    зяй
    0.34
     bring
    0.34
     Bring
    0.34
    Activations Density 0.000%

    No Known Activations