© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41291
    Prev
    Next
    INDEX
    Explanations

    display settings

    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_22_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
     rely
    0.43
     procl
    0.41
     relying
    0.40
    haal
    0.39
    utum
    0.39
    샨
    0.39
    업
    0.39
    ornos
    0.38
     offent
    0.38
     reliance
    0.38
    POSITIVE LOGITS
    ക്കളെ
    0.45
    ⮚
    0.45
    📚
    0.44
     शेष
    0.43
     打开
    0.43
     ใส่
    0.42
     Tell
    0.42
     Spearman
    0.41
     Conservative
    0.41
     Petit
    0.41
    Activations Density 0.001%

    No Known Activations