© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 11636
    Prev
    Next
    INDEX
    Explanations

    architecture and design

    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_13_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
    time
    0.27
    ্ত
    0.25
     Spending
    0.24
     Zweck
    0.24
    ▬▬▬▬
    0.23
     Charity
    0.23
     Bundest
    0.23
    時
    0.22
    lemon
    0.22
    ➽
    0.22
    POSITIVE LOGITS
    Kotlin
    0.23
     ovar
    0.22
     axially
    0.22
     academ
    0.22
     oneness
    0.21
    TRANS
    0.21
     Koval
    0.21
     linearly
    0.21
    {})
    0.21
     analyzers
    0.21
    Activations Density 0.012%

    No Known Activations