© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214371
    Prev
    Next
    INDEX
    Explanations

    electron, selective

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     ریز
    0.37
    圯
    0.37
    Pitt
    0.36
     underground
    0.36
     খুঁজ
    0.35
     解
    0.35
     تلق
    0.35
     Underground
    0.33
    =\""
    0.33
    asarray
    0.33
    POSITIVE LOGITS
     Electron
    0.59
    Electron
    0.53
     electron
    0.50
    Emp
    0.43
     Emp
    0.42
     Selective
    0.42
    electron
    0.42
    谀
    0.41
     selective
    0.41
     दवाओं
    0.41
    Activations Density 0.000%

    No Known Activations