© 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. 41249
    Prev
    Next
    INDEX
    Explanations

    of specialized services

    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
     전화
    0.20
    9
    0.19
    Jan
    0.18
     అందించ
    0.18
    3
    0.18
    ちゃん
    0.18
    น
    0.18
     な
    0.18
     dàn
    0.18
    IZ
    0.17
    POSITIVE LOGITS
    pidos
    0.22
     Mahm
    0.22
    liny
    0.22
     herhangi
    0.21
     ataupun
    0.21
    ினை
    0.20
     थर्म
    0.20
     zuf
    0.20
     superstars
    0.20
    haviour
    0.20
    Activations Density 0.052%

    No Known Activations