© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47241
    Prev
    Next
    INDEX
    Explanations

    Must have

    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_3_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
    ਮ
    0.61
     championnat
    0.61
    সময়
    0.60
    टाइम
    0.60
    تی
    0.60
    ถูกต้อง
    0.59
    ター
    0.59
     motorcycle
    0.57
    _=
    0.57
    常に
    0.57
    POSITIVE LOGITS
    at
    0.89
    ↵
    0.75
    ل
    0.64
    quela
    0.64
    л
    0.64
     partícula
    0.59
     liberación
    0.58
    an
    0.57
    atka
    0.57
    ت
    0.57
    Activations Density 0.002%

    No Known Activations