© 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. 92054
    Prev
    Next
    INDEX
    Explanations

    universal human basic donor

    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
    он
    0.86
    and
    0.79
     bude
    0.74
    গুলো
    0.71
    να
    0.70
     može
    0.68
    ISES
    0.68
     parece
    0.67
    ك
    0.66
     môže
    0.65
    POSITIVE LOGITS
    )
    0.72
    gard
    0.67
    ds
    0.64
    port
    0.61
    ry
    0.61
    gem
    0.60
    rest
    0.60
    mental
    0.60
    一条
    0.58
    d
    0.58
    Activations Density 0.024%

    No Known Activations