© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218278
    Prev
    Next
    INDEX
    Explanations

    fragrance notes

    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
     spark
    0.41
     श्र
    0.40
    Spark
    0.40
     leaped
    0.39
    念
    0.39
     aesthetic
    0.38
    涤
    0.38
     抗
    0.38
    ថា
    0.37
     müz
    0.37
    POSITIVE LOGITS
     Parfum
    0.46
     Morr
    0.43
     Cigar
    0.43
     opium
    0.41
     wprowad
    0.40
    斂
    0.39
    conditioning
    0.39
     vir
    0.39
     tomber
    0.38
    opium
    0.38
    Activations Density 0.002%

    No Known Activations