© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241529
    Prev
    Next
    INDEX
    Explanations

    list items

    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_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ody
    0.39
    dy
    0.38
     இற
    0.38
    소서
    0.38
    套装
    0.38
     descriptions
    0.37
    frames
    0.37
    帯
    0.37
     Frames
    0.37
    фектив
    0.36
    POSITIVE LOGITS
     вклю
    0.44
     snapped
    0.41
     taille
    0.40
     included
    0.39
     elegir
    0.38
     सम्मिलित
    0.38
     snapping
    0.37
    implemented
    0.37
     appointing
    0.36
    ╯
    0.36
    Activations Density 0.001%

    No Known Activations