© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24957
    Prev
    Next
    INDEX
    Explanations

    Founded

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     м
    0.62
    мено
    0.44
    άσ
    0.42
     m
    0.40
    ρί
    0.36
     наме
    0.35
    梼
    0.35
     ciała
    0.35
    Ь
    0.35
    徊
    0.34
    POSITIVE LOGITS
     основа
    0.95
     поло
    0.80
    uut
    0.55
     founded
    0.54
    поло
    0.54
    founded
    0.53
    Founded
    0.51
     Founded
    0.51
     состоя
    0.49
     aikana
    0.40
    Activations Density 0.006%

    No Known Activations