© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31996
    Prev
    Next
    INDEX
    Explanations

    sugar crystallization or ratio

    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_31_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
    Sugar
    0.49
     साखर
    0.48
     сахар
    0.47
     Sugar
    0.46
     sugar
    0.45
     Candy
    0.43
    砂糖
    0.43
    糖
    0.42
    Candy
    0.42
     शुगर
    0.42
    POSITIVE LOGITS
     loosened
    0.41
     Aad
    0.40
     botão
    0.38
     consecrated
    0.38
    沟
    0.38
     inseg
    0.37
     sentido
    0.37
     instructional
    0.36
    appliquer
    0.36
     Sporting
    0.36
    Activations Density 0.037%

    No Known Activations