© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54491
    Prev
    Next
    INDEX
    Explanations

    riddle

    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_31_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
     dată
    0.42
     keyst
    0.41
     paragon
    0.41
     sensi
    0.39
    isk
    0.38
     zeal
    0.38
     nano
    0.38
     readiness
    0.38
    난
    0.38
     kuwa
    0.37
    POSITIVE LOGITS
    getParameters
    0.38
    CLAIM
    0.38
     Volker
    0.37
     Antoine
    0.37
    登記
    0.37
    ClCompile
    0.36
     Beno
    0.36
    आइए
    0.36
    Ἠ
    0.36
    ']],
    0.36
    Activations Density 0.004%

    No Known Activations