© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 30911
    Prev
    Next
    INDEX
    Explanations

    acquaintance

    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_50_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
     Ash
    0.41
     Chanel
    0.40
    Ash
    0.38
     sampler
    0.38
     ActionMode
    0.38
    istaa
    0.38
     Ist
    0.37
    avk
    0.37
    翔
    0.37
     Fy
    0.37
    POSITIVE LOGITS
    aint
    0.48
     русской
    0.41
     કે
    0.40
     Verne
    0.39
     ain
    0.39
     Nancy
    0.38
    Ска
    0.36
    Nancy
    0.36
    ainte
    0.36
     Кали
    0.35
    Activations Density 0.001%

    No Known Activations