© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207447
    Prev
    Next
    INDEX
    Explanations

    flat

    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_46_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
    Fu
    0.49
    Ful
    0.49
     Ful
    0.48
     Fu
    0.44
     ભે
    0.40
    풀
    0.40
     Fuller
    0.39
    కపో
    0.39
     ful
    0.38
    凝
    0.38
    POSITIVE LOGITS
    অ
    0.39
     ਐ
    0.37
    öre
    0.37
     design
    0.37
     GCBO
    0.35
     설계
    0.35
    eid
    0.34
    design
    0.34
     immédi
    0.34
    eulerAngles
    0.33
    Activations Density 0.001%

    No Known Activations