© 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. 26626
    Prev
    Next
    INDEX
    Explanations

    need or have questions

    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
    काई
    0.40
    裝置
    0.39
     Kirch
    0.37
     broad
    0.36
     choice
    0.36
    valued
    0.36
    組合
    0.36
     প্রধান
    0.35
    値
    0.35
    otypic
    0.35
    POSITIVE LOGITS
     rivol
    0.40
     Jerusal
    0.39
     शही
    0.37
    bewerken
    0.36
    voc
    0.36
     congrats
    0.36
    ἡ
    0.36
    浄
    0.36
     Congr
    0.35
    PathDirectory
    0.35
    Activations Density 0.025%

    No Known Activations