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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80397
    Prev
    Next
    INDEX
    Explanations

    follow

    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_53_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
    eches
    0.41
    ು
    0.40
    이는
    0.38
    ර්ග
    0.38
     semigroup
    0.38
    োরের
    0.38
    üglich
    0.37
    ರೆಯ
    0.37
    saw
    0.37
    験
    0.37
    POSITIVE LOGITS
     Samuels
    0.46
     Andreas
    0.41
     Adelaide
    0.40
     Crystal
    0.40
     crystal
    0.40
     Peabody
    0.39
     חו
    0.38
     Dexter
    0.38
     Zad
    0.38
    水晶
    0.38
    Activations Density 0.001%

    No Known Activations