© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109517
    Prev
    Next
    INDEX
    Explanations

    out

    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_1_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
     be
    1.08
     I
    0.84
     her
    0.82
     এ
    0.82
     an
    0.80
    {//
    0.77
    ILLS
    0.76
    м
    0.76
     interni
    0.75
    ک
    0.75
    POSITIVE LOGITS
    تي
    0.98
    ности
    0.93
    ્સ
    0.88
    다음
    0.88
    is
    0.85
    ล
    0.84
    تين
    0.82
    ων
    0.81
    ти
    0.79
    ስ
    0.77
    Activations Density 0.008%

    No Known Activations