© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148491
    Prev
    Next
    INDEX
    Explanations

    shell commands to execute

    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_23_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
     интересный
    0.45
     частью
    0.44
    ualmente
    0.43
     производи
    0.42
     брать
    0.42
     النموذج
    0.40
    ":"
    0.39
     AMAZ
    0.39
    ">//
    0.39
     الصحية
    0.38
    POSITIVE LOGITS
     rejoicing
    0.54
     rejoice
    0.47
    nostic
    0.44
    otions
    0.43
     harder
    0.42
     Jubilee
    0.41
    jub
    0.41
    າດ
    0.41
     mediation
    0.41
     over
    0.41
    Activations Density 0.002%

    No Known Activations