© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2158
    Prev
    Next
    INDEX
    Explanations

    same or similar

    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_40_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
     COMM
    0.37
     খুবই
    0.37
     বিশেষভাবে
    0.36
     osl
    0.35
     extraordinarily
    0.35
    ரியில்
    0.35
     KH
    0.35
    当中
    0.35
     "{
    0.35
     TA
    0.35
    POSITIVE LOGITS
     identical
    0.69
    identical
    0.67
    同
    0.62
    same
    0.61
     nhau
    0.59
     identically
    0.59
     samme
    0.55
    同じ
    0.52
    Same
    0.52
    相同的
    0.52
    Activations Density 0.090%

    No Known Activations