© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248244
    Prev
    Next
    INDEX
    Explanations

    smoking

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ئێ
    0.44
    이브
    0.38
     jí
    0.36
    琰
    0.35
     rak
    0.34
     ది
    0.34
    蔺
    0.34
     &,
    0.33
    enska
    0.33
    ermott
    0.33
    POSITIVE LOGITS
     weed
    0.63
    Mari
    0.52
     marijuana
    0.51
     Weed
    0.50
     cannabis
    0.50
    mari
    0.49
     Мари
    0.48
     marihuana
    0.47
     Mari
    0.47
     mari
    0.47
    Activations Density 0.001%

    No Known Activations