© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 55002
    Prev
    Next
    INDEX
    Explanations

    actions and choices

    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_55_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
     Streaming
    0.41
     файла
    0.39
     item
    0.38
     Engineer
    0.37
    streaming
    0.37
     streaming
    0.37
    爌
    0.36
     ENGINEER
    0.36
    Engineer
    0.35
    ྨ
    0.35
    POSITIVE LOGITS
     choices
    0.50
    Choices
    0.44
    States
    0.43
    choices
    0.43
     states
    0.43
     deeds
    0.42
     conducts
    0.42
     Choices
    0.42
     redirect
    0.40
     Action
    0.40
    Activations Density 0.013%

    No Known Activations