© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135377
    Prev
    Next
    INDEX
    Explanations

    arrogant

    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_6_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
    )
    1.27
     critic
    1.26
     by
    1.17
    ל
    1.12
    '
    1.10
    ו
    1.05
     workaround
    1.02
     self
    0.98
     businessman
    0.97
     It
    0.96
    POSITIVE LOGITS
    ğlu
    1.08
    ને
    1.07
    ın
    1.05
    givers
    1.04
    g
    1.02
     Adası
    1.00
    oy
    1.00
     Балтбет
    0.99
    від
    0.97
    colour
    0.96
    Activations Density 0.000%

    No Known Activations