© 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. 127793
    Prev
    Next
    INDEX
    Explanations

    StableLM, liability, diffusion

    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
    e
    0.73
     двох
    0.70
    o
    0.63
    i
    0.57
     bastion
    0.55
     deplorable
    0.54
     август
    0.54
     computationally
    0.53
    bindingFields
    0.53
     llevaba
    0.52
    POSITIVE LOGITS
    یس
    0.95
     to
    0.85
    ید
    0.75
    ری
    0.73
    یت
    0.73
    of
    0.70
    کل
    0.70
    り
    0.69
    ми
    0.69
     smiles
    0.69
    Activations Density 0.001%

    No Known Activations