© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62321
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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_11_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
    '
    0.56
    IFT
    0.54
    enden
    0.52
     म
    0.51
     rys
    0.50
     미국의
    0.49
    ende
    0.49
     ler
    0.49
    ;
    0.48
     lir
    0.48
    POSITIVE LOGITS
    டி
    0.49
    glasses
    0.48
     slideshow
    0.47
     Vegas
    0.47
    ാല്‍
    0.46
    लक्ष्मी
    0.45
    glass
    0.45
    どう
    0.45
    خاب
    0.45
    ソフトウェア
    0.45
    Activations Density 0.001%

    No Known Activations