© 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. 10359
    Prev
    Next
    INDEX
    Explanations

    public class/fn

    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
    Man
    0.12
    hend
    0.12
    Correlation
    0.12
    Const
    0.11
     CRE
    0.11
    PARATOR
    0.11
    ライダー
    0.11
    htein
    0.11
    ⓜ
    0.11
    ירה
    0.11
    POSITIVE LOGITS
     পরও
    0.11
    မ်း
    0.11
     quaint
    0.10
     intArray
    0.10
    涸
    0.10
     Wanna
    0.10
    ብስብ
    0.10
    ครง
    0.10
     ranging
    0.10
     ৃ
    0.10
    Activations Density 0.042%

    No Known Activations