© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84817
    Prev
    Next
    INDEX
    Explanations

    paradigms

    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_0_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
     was
    1.66
    ه
    1.59
    2
    1.53
    는
    1.53
     I
    1.51
    是
    1.51
     to
    1.50
    a
    1.48
    I
    1.44
     and
    1.37
    POSITIVE LOGITS
     avocat
    1.60
     amico
    1.50
     azione
    1.49
     allemand
    1.48
     atteindre
    1.48
     ﺍﻟ
    1.44
     analisi
    1.43
     і
    1.42
     ی
    1.40
    ною
    1.40
    Activations Density 0.000%

    No Known Activations