© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211542
    Prev
    Next
    INDEX
    Explanations

    all rows and unique categories

    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_20_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
    %.
    0.32
     سٹ
    0.31
     sciences
    0.30
    }%
    0.30
    開発
    0.29
     vol
    0.29
     alcal
    0.29
    食事
    0.29
    %).
    0.29
     waters
    0.28
    POSITIVE LOGITS
    شق
    0.36
     प्रणाम
    0.36
    ଈ
    0.36
    ДИ
    0.36
     forgive
    0.35
    addPreferredGap
    0.35
    ično
    0.34
    sequential
    0.33
    ொண்டு
    0.33
    മാന
    0.33
    Activations Density 0.031%

    No Known Activations