© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207787
    Prev
    Next
    INDEX
    Explanations

    stochastic dynamic

    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_46_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
     Friendship
    0.45
     pd
    0.44
    Pd
    0.43
     Courtney
    0.43
     Gul
    0.41
     Xuân
    0.40
    Arn
    0.40
     Philips
    0.40
    pd
    0.39
    ښ
    0.39
    POSITIVE LOGITS
     stochastic
    0.51
    Heter
    0.50
     Heter
    0.49
     heter
    0.47
     Stochastic
    0.43
    dynamic
    0.42
     Dynamic
    0.41
    hept
    0.41
     heterod
    0.41
     dynamic
    0.41
    Activations Density 0.039%

    No Known Activations