© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54688
    Prev
    Next
    INDEX
    Explanations

    instructions, choose the best answer

    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_31_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
    続く
    0.44
     提供
    0.42
     vidéos
    0.39
    殁
    0.38
     एक्सप्ले
    0.38
    Bian
    0.38
    ojure
    0.37
     Tutorials
    0.37
    提供
    0.37
     dara
    0.37
    POSITIVE LOGITS
    ാനും
    0.45
    ಿಣ
    0.38
     Allerg
    0.36
    蟎
    0.36
     applying
    0.35
     doen
    0.35
    珏
    0.35
    齦
    0.35
     laughing
    0.34
    ုန်း
    0.34
    Activations Density 0.003%

    No Known Activations