© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209854
    Prev
    Next
    INDEX
    Explanations

    ie, os, á, ü, м, л, ב, 리, يس, ف

    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_5_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
    ↵
    0.32
    a
    0.32
    aun
    0.31
    -
    0.31
    3
    0.31
    aaaa
    0.31
    ați
    0.29
     welke
    0.29
     clo
    0.28
             
    0.28
    POSITIVE LOGITS
    ü
    0.50
     It
    0.48
    м
    0.46
    л
    0.46
    ב
    0.45
    리
    0.44
    á
    0.42
    یس
    0.42
    ف
    0.40
    ме
    0.40
    Activations Density 0.000%

    No Known Activations