© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57495
    Prev
    Next
    INDEX
    Explanations

    The

    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_59_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
     rebuke
    0.44
    বারেই
    0.41
     penchant
    0.39
     propensity
    0.38
     theme
    0.38
     portrayal
    0.37
    }`,
    0.37
    }`));
    0.37
     Operand
    0.37
     psyche
    0.36
    POSITIVE LOGITS
     language
    0.99
    language
    0.98
    Language
    0.97
     Language
    0.91
    语言
    0.85
     भाषा
    0.84
    語言
    0.80
     lenguaje
    0.79
     Sprache
    0.78
     язык
    0.77
    Activations Density 0.008%

    No Known Activations