© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6246
    Prev
    Next
    INDEX
    Explanations

    writing style quality

    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_40_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
     poems
    0.94
     poem
    0.93
     Poems
    0.90
    poem
    0.89
    poems
    0.87
     Poem
    0.86
    Poems
    0.85
     book
    0.84
     책
    0.82
     książ
    0.80
    POSITIVE LOGITS
     Style
    0.44
     Kame
    0.42
     plotted
    0.38
     stijl
    0.37
     plots
    0.37
     β
    0.37
     plotting
    0.36
     style
    0.36
     Nations
    0.36
     בל
    0.35
    Activations Density 0.131%

    No Known Activations