© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29853
    Prev
    Next
    INDEX
    Explanations

    platform system or name

    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_40_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
     narrowly
    0.37
    samb
    0.36
     syntactic
    0.34
     이용
    0.34
    顺利
    0.34
     Amish
    0.33
    ओं
    0.33
    只能
    0.32
    ❿
    0.32
    sigmoid
    0.32
    POSITIVE LOGITS
    気
    0.44
     Independ
    0.40
     independents
    0.40
     Trichodesmium
    0.39
     Independent
    0.38
    Independent
    0.38
     indépend
    0.38
     independente
    0.37
     Natura
    0.37
     detection
    0.36
    Activations Density 0.001%

    No Known Activations