© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 103018
    Prev
    Next
    INDEX
    Explanations

    water solubility and aqueous solutions

    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_14_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
     program
    0.52
     wèi
    0.52
    <0x98>
    0.50
     comprende
    0.49
     Rept
    0.48
     bearing
    0.48
     whiskey
    0.47
    <0x9B>
    0.47
    oluene
    0.47
     network
    0.46
    POSITIVE LOGITS
    vstack
    0.59
    Combin
    0.58
    Given
    0.58
    jane
    0.55
    indian
    0.55
    kań
    0.55
    Geometry
    0.54
    Other
    0.53
    .”[
    0.53
    ⅔
    0.52
    Activations Density 0.007%

    No Known Activations