© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74514
    Prev
    Next
    INDEX
    Explanations

    logstash config

    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_31_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
     pillow
    0.43
    '&&
    0.42
    pillow
    0.39
    Convention
    0.39
    Յ
    0.38
     leveling
    0.37
    Navigate
    0.37
    ట్టు
    0.36
    സ്ട
    0.36
     telefonu
    0.36
    POSITIVE LOGITS
     Summer
    0.39
    Pent
    0.35
    ҉
    0.35
    θηκε
    0.35
     дана
    0.35
    agens
    0.33
    Classe
    0.33
     Apar
    0.33
    душ
    0.33
    歙
    0.33
    Activations Density 0.021%

    No Known Activations