© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232453
    Prev
    Next
    INDEX
    Explanations

    unpopular pleasant

    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_32_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
     specification
    0.38
    specification
    0.36
     Specifications
    0.35
    莧
    0.34
     monomial
    0.34
    ряда
    0.33
     expresión
    0.33
    వం
    0.33
    謙
    0.33
     Landscape
    0.32
    POSITIVE LOGITS
     unpopular
    0.73
    popularity
    0.68
     popularity
    0.66
    Popular
    0.52
     인기
    0.50
     pleasant
    0.50
     लोकप्रिय
    0.50
    人気
    0.49
     Popular
    0.48
    popular
    0.48
    Activations Density 0.039%

    No Known Activations