© 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. 46238
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    蓑
    0.38
    我认为
    0.38
     невероят
    0.37
     количество
    0.37
     Dorm
    0.37
     dorm
    0.36
     that
    0.36
     deployed
    0.36
    ্ত
    0.36
    randrange
    0.36
    POSITIVE LOGITS
    Ũ
    0.47
    Ẽ
    0.45
    ഗു
    0.43
    ႄ
    0.41
    ᾖ
    0.40
    🖖
    0.39
     ។
    0.39
    FocusValue
    0.39
    ಗೋ
    0.38
     teda
    0.37
    Activations Density 0.000%

    No Known Activations