© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40698
    Prev
    Next
    INDEX
    Explanations

    EIA energy information and predictions

    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_11_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
    ucidation
    0.46
    mentation
    0.45
     t
    0.45
    istet
    0.43
     Up
    0.43
    їв
    0.42
    cula
    0.42
    েক্টর
    0.42
    пиона
    0.42
     fortfarande
    0.41
    POSITIVE LOGITS
     эш
    0.56
    FN
    0.53
    H
    0.53
    လုပ်
    0.50
    SM
    0.50
     ಫ
    0.50
     godzin
    0.49
     پہا
    0.49
     günlük
    0.49
    전
    0.48
    Activations Density 0.016%

    No Known Activations