© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154538
    Prev
    Next
    INDEX
    Explanations

    Otsu thresholding

    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_50_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
    kel
    0.49
    Kel
    0.43
    тила
    0.42
     Kel
    0.41
     kel
    0.40
    Ｋ
    0.40
    ஜக
    0.40
     टेलीग्राम
    0.39
    ENCI
    0.39
    阃
    0.39
    POSITIVE LOGITS
     purus
    0.42
    uses
    0.41
    us
    0.40
    ভূম
    0.39
    ዋል
    0.38
    use
    0.38
     Ping
    0.38
     Yong
    0.38
     वित
    0.38
     waffles
    0.37
    Activations Density 0.000%

    No Known Activations