© 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. 154596
    Prev
    Next
    INDEX
    Explanations

    wine and places

    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
    Not in Any Lists

    No Comments

    Negative Logits
     паз
    0.39
     сту
    0.38
     оказыва
    0.38
    plein
    0.38
     लेकर
    0.37
    āli
    0.37
    ぷ
    0.37
    సుకు
    0.36
     क्विक
    0.35
    ぜ
    0.35
    POSITIVE LOGITS
    Gall
    0.43
    icc
    0.41
    batim
    0.39
    Thi
    0.38
     freelance
    0.38
    stimulation
    0.38
    IA
    0.38
    Freel
    0.37
     Pareto
    0.37
     switch
    0.37
    Activations Density 0.000%

    No Known Activations