© 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. 195273
    Prev
    Next
    INDEX
    Explanations

    button clicks

    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
    єю
    0.39
     yaşayan
    0.36
    camore
    0.33
    Borderless
    0.33
    pose
    0.32
    ঘন
    0.32
     मोड
    0.31
    umetric
    0.31
    /*.
    0.30
    ويب
    0.30
    POSITIVE LOGITS
     was
    0.58
    Was
    0.58
     Was
    0.52
     была
    0.52
     była
    0.51
    was
    0.48
     было
    0.48
     был
    0.45
     était
    0.44
     byla
    0.44
    Activations Density 0.001%

    No Known Activations