© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 804
    Prev
    Next
    INDEX
    Explanations

    My core guidelines

    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_39_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
    fragt
    0.37
     hooking
    0.37
    oderma
    0.36
     Priest
    0.36
     Wayback
    0.36
     তাড়াতাড়ি
    0.35
     Bench
    0.35
    ombies
    0.35
    自由に
    0.34
    }`).
    0.34
    POSITIVE LOGITS
    built
    0.42
    Behaviour
    0.42
     professional
    0.41
     built
    0.39
    Operating
    0.39
    Built
    0.38
    скага
    0.38
    allocated
    0.38
    訓練
    0.38
     प्रशिक्षित
    0.38
    Activations Density 0.224%

    No Known Activations