© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 140140
    Prev
    Next
    INDEX
    Explanations

    trapped under rubble

    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_37_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
     IC
    0.54
     ic
    0.47
     Ic
    0.46
     hammered
    0.43
     Hammer
    0.42
     destiné
    0.42
     pounded
    0.41
     hammer
    0.41
     आईसी
    0.40
    锤
    0.40
    POSITIVE LOGITS
     Unter
    0.42
     schul
    0.38
     Niss
    0.38
     federation
    0.38
     feder
    0.38
    )=[
    0.38
    فرم
    0.37
    SpacerItem
    0.37
     overturning
    0.37
     फेड
    0.37
    Activations Density 0.001%

    No Known Activations