© 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. 215079
    Prev
    Next
    INDEX
    Explanations

    future readiness and action

    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
    额
    0.42
    的支持
    0.38
     परवानगी
    0.37
    呵
    0.36
    rupulous
    0.36
     виклика
    0.35
    稳定性
    0.35
    ঘ
    0.34
    希
    0.34
    比例
    0.34
    POSITIVE LOGITS
     Prepared
    0.46
     seizing
    0.42
     seized
    0.41
     capturing
    0.41
     skills
    0.40
     education
    0.40
     position
    0.40
     seize
    0.40
     Navigator
    0.39
     Positions
    0.38
    Activations Density 0.031%

    No Known Activations