© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102689
    Prev
    Next
    INDEX
    Explanations

    next best 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_14_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Payments
    0.56
    なかなか
    0.55
    ീല
    0.54
     gonna
    0.53
    資金
    0.53
    芾
    0.53
    ਦੀ
    0.52
     میوز
    0.52
     méthodique
    0.52
    ≿
    0.51
    POSITIVE LOGITS
    Env
    0.48
     एक
    0.47
    Pers
    0.46
     {
    0.46
     unge
    0.45
     renversement
    0.45
    malt
    0.45
     října
    0.45
     insurg
    0.44
     eine
    0.43
    Activations Density 0.007%

    No Known Activations