© 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. 211054
    Prev
    Next
    INDEX
    Explanations

    logic puzzles and paradoxes

    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
     substr
    0.29
     primary
    0.27
    blum
    0.27
     linie
    0.27
     r
    0.27
     lin
    0.27
     agar
    0.27
     suppressor
    0.27
     machin
    0.27
     adrenalin
    0.27
    POSITIVE LOGITS
     เจ้า
    0.30
    UIColor
    0.30
     آخر
    0.29
    κα
    0.28
     głównie
    0.27
    <0x8F>
    0.26
    Pierce
    0.26
    珠宝
    0.26
    ീയ
    0.26
     🔥
    0.26
    Activations Density 0.008%

    No Known Activations