© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235682
    Prev
    Next
    INDEX
    Explanations

    people search for

    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_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     undermine
    0.39
    য়ের
    0.38
    administration
    0.37
    ታዊ
    0.36
    speople
    0.36
    시키는
    0.36
     prioritise
    0.36
    )^{-
    0.36
     lament
    0.35
     unimplemented
    0.35
    POSITIVE LOGITS
     variedade
    0.40
     Володи
    0.39
    เป
    0.38
     প্রমুখ
    0.38
    趸
    0.37
    Evet
    0.37
     дорого
    0.36
     మహి
    0.36
    อิน
    0.36
     ปลา
    0.35
    Activations Density 0.006%

    No Known Activations