© 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. 41124
    Prev
    Next
    INDEX
    Explanations

    our company/team/data

    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
    飘
    0.29
     π
    0.27
     Wärm
    0.27
    DistanceFrom
    0.27
     thisComponent
    0.26
     bőr
    0.26
     кожи
    0.26
     최초
    0.26
    મેન્ટ
    0.26
     protons
    0.26
    POSITIVE LOGITS
     भागात
    0.31
    idders
    0.30
    ？
    0.30
     schre
    0.28
    ：“
    0.28
    irse
    0.28
     afectada
    0.28
     Segment
    0.28
     As
    0.28
    によ
    0.27
    Activations Density 0.008%

    No Known Activations