© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 116416
    Prev
    Next
    INDEX
    Explanations

    downloading pirated movies

    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_38_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
    Martinez
    0.45
     Owner
    0.42
     OWNER
    0.41
     sparkly
    0.40
    栘
    0.40
     Potato
    0.40
    臾
    0.39
    咖啡
    0.39
     पुरंदरे
    0.39
     DIY
    0.39
    POSITIVE LOGITS
    tile
    0.41
    ibile
    0.40
     ApiException
    0.38
    binomial
    0.37
    hot
    0.37
    aira
    0.36
    rcParams
    0.36
    étation
    0.36
     stratum
    0.35
    ievements
    0.35
    Activations Density 0.004%

    No Known Activations