© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67583
    Prev
    Next
    INDEX
    Explanations

    brute force

    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_41_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
    ificado
    0.45
    汲
    0.40
    剡
    0.40
    ENDMENT
    0.39
    ગી
    0.38
    响起
    0.38
     экологи
    0.36
    튜
    0.36
    alassem
    0.36
    छाड़
    0.35
    POSITIVE LOGITS
     force
    2.14
    force
    1.90
    Force
    1.79
    力
    1.77
     Force
    1.73
     fuerza
    1.73
     FORCE
    1.67
     forza
    1.64
     força
    1.58
    FORCE
    1.48
    Activations Density 0.091%

    No Known Activations