© 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. 35811
    Prev
    Next
    INDEX
    Explanations

    quantum bits and states

    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
    alloween
    0.46
     centrales
    0.46
     avrebbe
    0.44
     insistence
    0.42
    ்சி
    0.42
     creases
    0.42
    䒾
    0.42
     WOULD
    0.42
     paradoxical
    0.42
    l
    0.42
    POSITIVE LOGITS
    hosting
    0.51
     येते
    0.48
    ५
    0.47
     घेतले
    0.46
    انی
    0.46
    انیه
    0.45
    ան
    0.45
    voting
    0.45
     ጥቅ
    0.44
    漾
    0.44
    Activations Density 0.041%

    No Known Activations