© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150805
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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_59_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
    陥
    0.29
    yfik
    0.28
    জাতি
    0.28
     बजे
    0.28
     alleviating
    0.28
     subjecting
    0.28
     foment
    0.26
     preclude
    0.26
    राणिक
    0.26
    ยิน
    0.26
    POSITIVE LOGITS
     胡
    0.41
     Vj
    0.40
     Hòa
    0.40
     ACD
    0.39
     Mikh
    0.38
     KQ
    0.38
     Playhouse
    0.38
     HX
    0.38
     Ulu
    0.38
     ദുൽ
    0.38
    Activations Density 0.017%

    No Known Activations