© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154691
    Prev
    Next
    INDEX
    Explanations

    drawing text

    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_23_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
    anesulf
    0.39
    ément
    0.38
    Dump
    0.38
    螳
    0.38
    пански
    0.38
     bữa
    0.38
    δευ
    0.38
     pelle
    0.37
     Group
    0.36
    Group
    0.36
    POSITIVE LOGITS
    uese
    0.40
    ach
    0.40
    ael
    0.38
    ette
    0.37
    ולם
    0.37
    owanego
    0.37
    elius
    0.37
    च
    0.37
    onego
    0.36
    ee
    0.36
    Activations Density 0.001%

    No Known Activations