© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63146
    Prev
    Next
    INDEX
    Explanations

    vocal cords

    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_46_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
     gastric
    0.46
     gast
    0.45
    胃
    0.43
    Gast
    0.40
     Bill
    0.40
     open
    0.39
    Bill
    0.38
     внутрен
    0.37
    Brady
    0.37
    欷
    0.36
    POSITIVE LOGITS
     απα
    0.44
     voglia
    0.42
    貓
    0.41
    ⟦
    0.40
    Talking
    0.39
    近似
    0.39
     Talking
    0.38
     कैंड
    0.38
    𝗽
    0.38
     desiderio
    0.38
    Activations Density 0.003%

    No Known Activations