© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209499
    Prev
    Next
    INDEX
    Explanations

    highest number, fastest pace, lowest percentage

    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_25_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
     gerekli
    0.40
    ాడు
    0.40
     необходимых
    0.40
    Proveedor
    0.39
     hábitos
    0.39
    каче
    0.39
    奻
    0.38
    羯
    0.38
    㻁
    0.38
    gada
    0.38
    POSITIVE LOGITS
     휘
    0.38
    
    0.37
     inflated
    0.36
    口气
    0.36
     brothers
    0.35
     workspace
    0.35
     whispered
    0.35
     >>=
    0.35
     늘
    0.34
     onstage
    0.34
    Activations Density 0.001%

    No Known Activations