© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52014
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    半年
    0.41
    ﹡
    0.38
    шчы
    0.37
    adanam
    0.37
    }_{{\
    0.36
     দুপুর
    0.36
     sostit
    0.36
    ሃኒ
    0.36
     कटौती
    0.35
    sourceEncoding
    0.35
    POSITIVE LOGITS
    fu
    0.39
    ,)
    0.37
     &,
    0.36
    combined
    0.36
     yerde
    0.36
    াসে
    0.36
     เด้อ
    0.36
    চিতে
    0.36
    어로
    0.35
    時間に
    0.35
    Activations Density 0.000%

    No Known Activations