© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115209
    Prev
    Next
    INDEX
    Explanations

    hence me

    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_27_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
     selling
    0.35
    狍
    0.32
    flächen
    0.30
     formative
    0.30
    Inner
    0.30
    ឱ្យ
    0.29
    打包
    0.29
    紝
    0.29
    Selling
    0.29
     অভিয
    0.29
    POSITIVE LOGITS
     echoed
    0.38
     вижу
    0.35
    假设
    0.33
     yours
    0.32
    假設
    0.32
    хам
    0.32
     Veneto
    0.31
     Congratulations
    0.31
     echo
    0.30
    atrix
    0.30
    Activations Density 0.007%

    No Known Activations