© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45616
    Prev
    Next
    INDEX
    Explanations

    give options

    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_22_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
     तत्काल
    0.33
    ","
    0.30
     प्रस्तावित
    0.29
    ಸ್
    0.28
     defibr
    0.28
    ','
    0.27
    ሃኒ
    0.27
    Х
    0.27
     proposed
    0.27
     fallback
    0.27
    POSITIVE LOGITS
     bước
    0.31
    ليل
    0.27
     kisah
    0.27
     perspectivas
    0.26
     Basement
    0.26
     숨
    0.25
     pasos
    0.25
     घरी
    0.25
     notizia
    0.25
    nga
    0.24
    Activations Density 0.037%

    No Known Activations