© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197937
    Prev
    Next
    INDEX
    Explanations

    "Okay?" or "Alright?"

    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_12_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
    ußen
    0.57
    𝟮
    0.57
    fahrung
    0.53
    ina
    0.53
    Dia
    0.52
    g
    0.52
    نع
    0.51
    día
    0.51
    f
    0.51
    anyaan
    0.50
    POSITIVE LOGITS
     rivalry
    0.66
    ลักษณะ
    0.59
     regimes
    0.54
    ে
    0.54
     calcul
    0.54
     jargon
    0.54
    격
    0.54
     reckless
    0.53
     olacak
    0.52
     Department
    0.52
    Activations Density 0.001%

    No Known Activations