© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18846
    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_15_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
     அவர்கள்
    0.57
     ори
    0.56
    рати
    0.55
     분위
    0.54
    ন্যবাদ
    0.54
     tijekom
    0.54
     Сла
    0.54
    땃
    0.54
    编程
    0.53
    نې
    0.53
    POSITIVE LOGITS
    y
    0.66
    fore
    0.62
    v
    0.61
    ad
    0.60
     politician
    0.60
    1
    0.59
    ed
    0.57
    ec
    0.57
    ate
    0.56
     businesswoman
    0.55
    Activations Density 0.001%

    No Known Activations