© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168814
    Prev
    Next
    INDEX
    Explanations

    more details

    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_34_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
     ഒന്ന്
    0.38
     sulphate
    0.37
     Wählen
    0.35
    ᅢ
    0.35
     Saat
    0.34
     ग्रंथ
    0.34
    বেদ
    0.34
     dane
    0.33
     cleanly
    0.33
    patient
    0.33
    POSITIVE LOGITS
     mengenai
    0.40
    案件
    0.40
    anik
    0.40
     tentang
    0.39
     unfamiliar
    0.39
     about
    0.39
    官
    0.39
     గురించి
    0.37
    uristic
    0.36
     பற்றி
    0.36
    Activations Density 0.000%

    No Known Activations