© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200789
    Prev
    Next
    INDEX
    Explanations

    Great

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     ч
    0.41
     xt
    0.38
     pre
    0.38
     Industries
    0.38
     i
    0.37
     Speedway
    0.37
    elly
    0.37
     DASH
    0.37
     שכ
    0.36
     Customs
    0.36
    POSITIVE LOGITS
    addComponent
    0.49
     imediatamente
    0.40
    appare
    0.40
    Conformance
    0.40
    lığını
    0.39
    ᕝ
    0.38
    liz
    0.38
    အစိတ်အပိုင်း
    0.38
    配列
    0.37
    ʔ
    0.37
    Activations Density 0.001%

    No Known Activations