© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5567
    Prev
    Next
    INDEX
    Explanations

    **

    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_38_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ół
    0.38
     oči
    0.31
    ý
    0.31
    Mart
    0.31
    ład
    0.30
    Up
    0.30
    Marg
    0.30
    ដ្ឋ
    0.30
    ո
    0.30
    relax
    0.29
    POSITIVE LOGITS
    
    0.31
    鹬
    0.29
     Centres
    0.29
     রাখে
    0.29
     Zeta
    0.29
     센터
    0.29
     Renewal
    0.28
    昻
    0.28
    녠
    0.28
     FIFO
    0.28
    Activations Density 0.002%

    No Known Activations