© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84634
    Prev
    Next
    INDEX
    Explanations

    electrostatic potential, forces, attraction, interactions, levitation, spinning, speakers

    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_0_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
    و
    1.90
    ন
    1.88
    н
    1.84
    ва
    1.74
    ن
    1.66
    ور
    1.63
    า
    1.51
    न
    1.49
    ри
    1.48
    л
    1.45
    POSITIVE LOGITS
    C
    1.62
    to
    1.48
    ta
    1.47
    ۔
    1.43
    。
    1.42
    ten
    1.41
    de
    1.34
    K
    1.34
    Max
    1.30
    R
    1.30
    Activations Density 0.000%

    No Known Activations