© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 106871
    Prev
    Next
    INDEX
    Explanations

    hello followed by greetings

    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_2_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
    kan
    1.17
    va
    1.10
     ấn
    1.10
    {
    1.09
    ING
    1.08
    '
    1.07
     έχ
    1.06
     adresse
    1.05
     an
    1.02
    ا
    1.02
    POSITIVE LOGITS
    ร
    1.45
    ل
    1.38
    র
    1.21
    ر
    1.17
    Ри
    1.16
    ान
    1.13
    ன்
    1.13
    ר
    1.10
    r
    1.02
    ान्
    1.01
    Activations Density 0.010%

    No Known Activations