© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155712
    Prev
    Next
    INDEX
    Explanations

    Topic

    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_60_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
     yana
    0.38
    傲
    0.38
    ल्ला
    0.38
     apare
    0.37
    ליה
    0.37
     éves
    0.37
    ।
    0.37
    ”、
    0.36
     الحركه
    0.36
    ),]),
    0.36
    POSITIVE LOGITS
    choices
    0.68
     choices
    0.61
    web
    0.61
     Choices
    0.60
     Rem
    0.57
    rem
    0.53
     web
    0.52
     water
    0.52
    water
    0.51
    Choices
    0.51
    Activations Density 0.003%

    No Known Activations