© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121326
    Prev
    Next
    INDEX
    Explanations

    continuous process, complex, multifaceted

    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_37_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
    不容易
    0.45
    一直是
    0.42
    something
    0.40
     আশীর
    0.39
    是一种
    0.38
     něco
    0.38
    밌
    0.38
     something
    0.38
    不易
    0.38
     चीज
    0.37
    POSITIVE LOGITS
     mall
    0.41
    RON
    0.41
     deviate
    0.39
     качестве
    0.38
     }{\
    0.38
     diverges
    0.38
     diverse
    0.38
    ետ
    0.38
     সামান্য
    0.38
     symbolically
    0.37
    Activations Density 0.009%

    No Known Activations