© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193756
    Prev
    Next
    INDEX
    Explanations

    pressure gradients

    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_15_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
    L
    0.59
    大
    0.56
    ang
    0.55
    ing
    0.55
    D
    0.53
    MAX
    0.52
    VPN
    0.52
    LZ
    0.51
    ة
    0.51
     tradition
    0.50
    POSITIVE LOGITS
     складу
    0.63
     phosphates
    0.46
    <unused11>
    0.45
    ,+
    0.44
     buckles
    0.44
     Magnesium
    0.43
    wounded
    0.43
     exchangers
    0.43
     catheters
    0.43
    phosphate
    0.43
    Activations Density 0.001%

    No Known Activations