© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79478
    Prev
    Next
    INDEX
    Explanations

    d) / c)

    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_31_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
     unskilled
    0.27
     прожи
    0.26
     mals
    0.25
     unnamed
    0.24
     যায়নি
    0.23
    кал
    0.23
    arit
    0.23
    <0x1D>
    0.23
     حياة
    0.23
    сня
    0.22
    POSITIVE LOGITS
    Networks
    0.29
    Discussion
    0.28
    Book
    0.28
    lesias
    0.26
    ADB
    0.26
    Programme
    0.26
    Island
    0.26
    Big
    0.26
    Channels
    0.26
    HMS
    0.26
    Activations Density 0.001%

    No Known Activations