© 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
    2. Gemma-3-27B-IT
    3. 29-GEMMASCOPE-2-TRANSCODER-262K
    4. 80817
    Prev
    Next
    INDEX
    Explanations

    numbers or abbreviations after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_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
     seag
    0.41
    を用いて
    0.38
     breadth
    0.38
     param
    0.37
    "]["
    0.36
     ('
    0.34
     dne
    0.34
    フ
    0.33
     ['
    0.33
    𝗅
    0.33
    POSITIVE LOGITS
     Recol
    0.39
     वैक्सीनेशन
    0.37
    rivez
    0.37
     Rides
    0.37
     kati
    0.36
    चार्ज
    0.36
     अपॉ
    0.35
     Tickets
    0.35
     आफ
    0.35
     Porto
    0.35
    Activations Density 0.000%

    No Known Activations