© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200331
    Prev
    Next
    INDEX
    Explanations

    organic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    arged
    0.39
    ୱ
    0.39
     nore
    0.38
     tep
    0.38
    bach
    0.37
     Tep
    0.35
     Nep
    0.35
    በ
    0.35
    lag
    0.34
     TSR
    0.34
    POSITIVE LOGITS
    Organic
    1.13
     Organic
    1.07
     organic
    1.02
    organic
    1.00
     organik
    0.94
     ऑर्गेनिक
    0.92
    有機
    0.90
    有机
    0.89
     organiques
    0.88
     organics
    0.86
    Activations Density 0.001%

    No Known Activations