© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65059
    Prev
    Next
    INDEX
    Explanations

    riddle "what am I"

    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_51_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
    大地
    0.39
     Rend
    0.38
     muted
    0.36
    Bearing
    0.36
    étaire
    0.36
    Honeycomb
    0.35
     Danielle
    0.34
     Danny
    0.34
    Danny
    0.34
    レ
    0.33
    POSITIVE LOGITS
     elastomer
    0.42
    ","/
    0.41
    titleMargin
    0.41
     Allocate
    0.40
     Elytres
    0.39
     chromosphere
    0.39
    廝
    0.39
    淒
    0.39
    ွမ်း
    0.38
    Allocate
    0.38
    Activations Density 0.000%

    No Known Activations